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

    Neuronpedia

    INDEX
    Explanations

    words related to occupations and social roles in a community

    oai_token-act-pair · gemini-2.0-flash

    Professions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     MainAxisSize
    -0.93
     '\\;'
    -0.90
    RectangleBorder
    -0.88
    saraba
    -0.83
    -0.82
    LEncoder
    -0.80
    RTEX
    -0.80
    WebControls
    -0.80
    нгред
    -0.79
     ModelRenderer
    -0.79
    POSITIVE LOGITS
    .
    0.48
    '
    0.40
    ;
    0.39
     ejecutivo
    0.38
     Ejecutivo
    0.36
    ,
    0.36
    :
    0.35
    (
    0.33
     
    0.33
    ’
    0.33
    Act Density 3.746%

    No Known Activations