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

    Neuronpedia

    INDEX
    Explanations

    either license

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pauses
    -0.07
    ctxt
    -0.06
     finan
    -0.06
     Contin
    -0.06
    adapt
    -0.06
     cages
    -0.06
    .Space
    -0.06
    .Context
    -0.06
    .Details
    -0.06
     vyjád
    -0.06
    POSITIVE LOGITS
     coach
    0.06
    心
    0.06
    ателя
    0.06
    ژ
    0.06
    some
    0.06
    ाव
    0.06
     laboratory
    0.06
    이는
    0.06
     {/*
    0.06
    .font
    0.06
    Act Density 0.002%

    No Known Activations