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

    Neuronpedia

    INDEX
    Explanations

    get

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Curr
    -0.08
     persist
    -0.07
    陆
    -0.07
    西瓜
    -0.07
    .addField
    -0.07
     spaces
    -0.07
     delights
    -0.07
     joys
    -0.07
     ofrece
    -0.07
    CLUDED
    -0.07
    POSITIVE LOGITS
    coli
    0.08
    獾
    0.07
    ў
    0.07
    isé
    0.07
     '"';↵
    0.07
    Ş
    0.07
     pakistan
    0.07
    arsi
    0.07
    읔
    0.07
    PH
    0.06
    Act Density 0.003%

    No Known Activations