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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -aged
    -0.07
     mắc
    -0.06
     حسن
    -0.06
     commissions
    -0.06
    guards
    -0.06
    615
    -0.06
    çok
    -0.06
    Fresh
    -0.06
    loop
    -0.06
     Vý
    -0.06
    POSITIVE LOGITS
    keleton
    0.07
    ovala
    0.07
    DOCKER
    0.06
    .norm
    0.06
    ,r
    0.06
    레
    0.06
    ै↵
    0.06
     trauma
    0.06
    _valor
    0.06
    unn
    0.06
    Act Density 0.046%

    No Known Activations