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

    Neuronpedia

    INDEX
    Explanations

    words describing jobs, roles or professional activity

    oai_token-act-pair · gemini-2.0-flash

    business personnel

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Majefty
    -0.73
     Efq
    -0.73
    []
    -0.72
     Shakspeare
    -0.68
     \\
    -0.67
    crollView
    -0.66
    ]:
    -0.65
     themſelves
    -0.65
    UnknownFields
    -0.64
     ſeveral
    -0.64
    POSITIVE LOGITS
    GOTREF
    0.68
    ьаж
    0.60
    UrlResolution
    0.44
    /
    0.42
    Хьажоргаш
    0.41
     كومونز
    0.39
     iyi
    0.39
    XmlEnum
    0.38
    Pyx
    0.37
    jooq
    0.37
    Act Density 1.482%

    No Known Activations