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

    Neuronpedia

    INDEX
    Explanations

    .Context

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     carving
    -0.07
     metal
    -0.06
    рус
    -0.06
    coef
    -0.06
    =password
    -0.06
     facets
    -0.06
    native
    -0.06
    �
    -0.06
     precipitation
    -0.06
     thoại
    -0.05
    POSITIVE LOGITS
     {-
    0.07
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.07
    クション
    0.07
    ›
    0.06
    Monthly
    0.06
    >true
    0.06
     entreprise
    0.06
    fails
    0.06
    晨
    0.06
    」（
    0.06
    Act Density 0.000%

    No Known Activations