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

    Neuronpedia

    INDEX
    Explanations

    significant indicators or markers related to numerical and statistical concepts

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

    starts with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     вообще
    -0.29
    จ
    -0.28
     slik
    -0.28
     syk
    -0.28
    list
    -0.26
    ver
    -0.26
    get
    -0.25
    山
    -0.24
    us
    -0.24
     Clark
    -0.24
    POSITIVE LOGITS
     nakalista
    0.76
    principalTable
    0.75
    StoryboardSegue
    0.72
     виправивши
    0.70
    setVerticalGroup
    0.69
    MLLoader
    0.69
     HasFactory
    0.69
    Vidite
    0.68
     estekak
    0.68
     GenerationType
    0.67
    Act Density 0.001%

    No Known Activations