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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wheeler
    -0.07
    多多
    -0.07
    节约
    -0.07
     increases
    -0.07
    ि�
    -0.07
    horn
    -0.07
    գ
    -0.07
     addition
    -0.07
     лет
    -0.07
    冻
    -0.07
    POSITIVE LOGITS
     każd
    0.08
    |array
    0.07
    上周
    0.07
    _manifest
    0.07
    arently
    0.07
    variably
    0.07
     WordPress
    0.07
     Sở
    0.07
    ometown
    0.07
    Dashboard
    0.07
    Act Density 0.003%

    No Known Activations