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

    Neuronpedia

    INDEX
    Explanations

    references to relationships and changes in relationship status or dynamics

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

    Following directional or numerical adverbs

    np_acts-logits-general · gemini-2.0-flash

    numerical change and direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RenderAtEndOf
    -0.68
    //
    -0.67
     فريبيس
    -0.66
    AccessFile
    -0.60
     صوتيه
    -0.59
    ponses
    -0.58
     onCreateView
    -0.56
    jalá
    -0.55
     élevées
    -0.55
    ResponseWriter
    -0.55
    POSITIVE LOGITS
     two
    0.58
     shaving
    0.58
     margin
    0.56
     shaved
    0.56
     five
    0.56
     several
    0.54
     three
    0.54
     ten
    0.53
    metik
    0.52
    ktop
    0.52
    Act Density 0.452%

    No Known Activations