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

    Neuronpedia

    INDEX
    Explanations

    winners and nominees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    znám
    -0.07
    _matrices
    -0.06
     forensic
    -0.06
     Prosecutor
    -0.06
    _skills
    -0.06
     estates
    -0.06
    .initState
    -0.06
     filles
    -0.06
    ीट
    -0.06
     CPC
    -0.06
    POSITIVE LOGITS
    >;↵
    0.07
     winners
    0.07
    <"
    0.07
     nalez
    0.06
    -fix
    0.06
     ấn
    0.06
     nachází
    0.06
    ホ
    0.06
    ğü
    0.06
    ('='
    0.06
    Act Density 0.011%

    No Known Activations