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

    Neuronpedia

    INDEX
    Explanations

    pronouns and their associated verbs or actions

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

    Text following first person pronouns

    np_acts-logits-general · gemini-2.0-flash

    we can

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rrggbb
    -0.54
    Datuak
    -0.54
    tagHelperRunner
    -0.51
     BoxDecoration
    -0.50
     kaarangay
    -0.43
    complexContent
    -0.42
    辕
    -0.41
    뀜
    -0.41
     Audiodateien
    -0.41
    المناصب
    -0.40
    POSITIVE LOGITS
    windowFixed
    0.53
     ironically
    0.49
     nahilalakip
    0.47
    <?
    0.46
     المعيارى
    0.46
     hardly
    0.46
    kijken
    0.45
    glich
    0.45
    principalColumn
    0.44
    aryen
    0.44
    Act Density 0.610%

    No Known Activations