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

    Neuronpedia

    INDEX
    Explanations

    first person pronouns followed directly by a copula or auxiliary verb

    oai_token-act-pair · gemini-2.0-flash

    questions and opinions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pung
    -0.48
    CompoundButton
    -0.48
    ాన
    -0.47
    CUSSION
    -0.47
    apunov
    -0.46
    fml
    -0.46
     faker
    -0.45
     demand
    -0.45
     carrier
    -0.45
    hamcrest
    -0.45
    POSITIVE LOGITS
     tartalomajánló
    0.68
     InputDecoration
    0.58
     ")");
    0.57
    KURZBESCHREIBUNG
    0.57
    Hentet
    0.56
    bewerken
    0.54
     виправивши
    0.54
     ModelExpression
    0.53
    endfor
    0.53
    protoc
    0.52
    Act Density 0.312%

    No Known Activations