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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating actions related to arriving, discovering, or understanding something

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

    how something happened or came to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.65
    AddTagHelper
    -0.49
    MigrationBuilder
    -0.41
    IonicModule
    -0.41
    PositiveButton
    -0.40
     Boek
    -0.40
    matchCondition
    -0.40
    hoga
    -0.39
    demic
    -0.38
    ğraf
    -0.38
    POSITIVE LOGITS
     why
    0.52
     origin
    0.51
     waarom
    0.49
     varför
    0.49
    why
    0.48
     dlaczego
    0.48
     pourquoi
    0.46
     Origin
    0.46
    Why
    0.44
     hvorfor
    0.44
    Act Density 0.014%

    No Known Activations