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

    Neuronpedia

    INDEX
    Explanations

    statistically significant phrases and elements

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

    beginning clauses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    migrationBuilder
    -0.72
     invokingState
    -0.57
    MLLoader
    -0.56
    ModelSerializer
    -0.56
    +#+#
    -0.56
     ddelweddau
    -0.54
    Дереккөздер
    -0.54
    ApiModel
    -0.52
    AnimationsModule
    -0.51
    JspWriter
    -0.51
    POSITIVE LOGITS
    ValueStyle
    0.40
     nahilalakip
    0.39
     hän
    0.37
    AndEndTag
    0.36
     “…
    0.33
    <!--[
    0.33
     Apalagi
    0.32
    Šaltiniai
    0.32
    +:+
    0.32
    “…
    0.31
    Act Density 0.040%

    No Known Activations