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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scope
    -0.07
    хід
    -0.07
    -lines
    -0.07
     tô
    -0.06
     exams
    -0.06
     scopes
    -0.06
    SJ
    -0.06
     USS
    -0.06
    paring
    -0.06
    Link
    -0.06
    POSITIVE LOGITS
     tapping
    0.07
     EFF
    0.06
    _die
    0.06
     jew
    0.06
    ACTION
    0.06
    *time
    0.06
     elapsedTime
    0.06
    reur
    0.05
    自动
    0.05
     Representation
    0.05
    Act Density 0.069%

    No Known Activations