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

    Neuronpedia

    INDEX
    Explanations

    bias

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '):
↵
    -0.06
    EmptyEntries
    -0.06
    .strictEqual
    -0.06
    >Show
    -0.06
    ingen
    -0.06
    cancel
    -0.06
    .bulk
    -0.06
    .pitch
    -0.06
     thắng
    -0.06
    .Class
    -0.06
    POSITIVE LOGITS
     bek
    0.07
    Benefits
    0.07
    tığını
    0.06
     العملية
    0.06
     documenting
    0.06
     yum
    0.06
     gsl
    0.06
    portion
    0.06
     Oct
    0.06
    Needed
    0.06
    Act Density 0.010%

    No Known Activations