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

    Neuronpedia

    INDEX
    Explanations

    code/technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     debates
    -0.08
    全球
    -0.07
    Mon
    -0.07
    927
    -0.07
    .setSelected
    -0.06
    ิโล
    -0.06
     yaz
    -0.06
    μων
    -0.06
    族自治
    -0.06
    ilon
    -0.06
    POSITIVE LOGITS
    (Form
    0.07
     userEmail
    0.06
    (tag
    0.06
    [op
    0.06
     instructional
    0.06
     gibt
    0.06
    /Library
    0.06
     }\
    0.06
     whitespace
    0.06
     Looks
    0.06
    Act Density 0.000%

    No Known Activations