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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    孙
    -0.07
     minlength
    -0.06
     Otherwise
    -0.06
    .bo
    -0.06
    ENV
    -0.06
     ub
    -0.06
    .do
    -0.06
     に
    -0.06
    Otherwise
    -0.06
    otherwise
    -0.06
    POSITIVE LOGITS
     Fade
    0.07
    вищ
    0.06
     conced
    0.06
    PathComponent
    0.06
    CALE
    0.06
    0.06
     فق
    0.06
     Freak
    0.06
     Vikings
    0.06
    其
    0.06
    Act Density 0.000%

    No Known Activations