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

    Neuronpedia

    INDEX
    Explanations

    math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afort
    -0.06
    .Marker
    -0.06
     згад
    -0.06
    .ones
    -0.06
    .SizeF
    -0.06
     Snow
    -0.06
    .sparse
    -0.06
    eria
    -0.06
     management
    -0.06
    acob
    -0.06
    POSITIVE LOGITS
    ;!
    0.07
    $item
    0.06
    -ever
    0.06
    ster
    0.06
     Рез
    0.06
     Horton
    0.06
     claims
    0.06
     reports
    0.06
    .hover
    0.06
     nested
    0.06
    Act Density 0.011%

    No Known Activations