Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    statements or phrases that express evaluations of people or concepts, particularly in relation to performance or merit

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Past tense auxiliary verbs

    np_acts-logits-general · gemini-2.0-flash

    was followed by adverb

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cipital
    -0.53
    Apparently
    -0.51
    się
    -0.50
     Apparently
    -0.49
     heißt
    -0.48
     apparently
    -0.48
     V
    -0.47
     recently
    -0.45
     recent
    -0.45
     P
    -0.45
    POSITIVE LOGITS
    ScopeManager
    0.84
     propOrder
    0.74
     Efq
    0.72
    WriteBarrier
    0.71
     دیکھیے
    0.70
    LEncoder
    0.68
    enterOuterAlt
    0.68
    BufferException
    0.67
    RTDA
    0.67
     <",
    0.67
    Act Density 0.527%

    No Known Activations