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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate the act of referencing or discussing specific claims or points of data

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

    Preceding adverbs or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    recognized was

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AutoScaleMode
    -0.84
    CloseOperation
    -0.83
    EndGlobalSection
    -0.74
     AssemblyCulture
    -0.71
    canestro
    -0.69
    Enlaces
    -0.65
    AutoScale
    -0.65
    idać
    -0.64
    Fordítás
    -0.64
    fitrión
    -0.63
    POSITIVE LOGITS
     незавершена
    0.70
     sumer
    0.52
     opri
    0.51
    them
    0.51
    ="+
    0.49
    =”
    0.48
    ㅐ
    0.48
     graden
    0.48
     Diri
    0.47
     chou
    0.47
    Act Density 1.177%

    No Known Activations