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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -help
    -0.07
     Co
    -0.07
     AU
    -0.07
     Purple
    -0.07
    Japan
    -0.07
    足球
    -0.06
     cites
    -0.06
     portrays
    -0.06
    _desc
    -0.06
     stories
    -0.06
    POSITIVE LOGITS
    ()):↵
    0.07
    TexCoord
    0.06
    .getTarget
    0.06
     высокой
    0.06
     murdering
    0.06
     Initial
    0.06
    Dec
    0.06
    acciones
    0.06
    ﾉ
    0.06
     Στα
    0.06
    Act Density 0.001%

    No Known Activations