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

    Neuronpedia

    INDEX
    Explanations

    need

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     xlabel
    -0.07
    -live
    -0.06
    decoded
    -0.06
     rozp
    -0.06
    ivan
    -0.06
    .getMessage
    -0.06
    اما
    -0.06
    429
    -0.06
     coeff
    -0.06
    radouro
    -0.06
    POSITIVE LOGITS
     SCC
    0.07
    _inv
    0.07
     grin
    0.06
    _seg
    0.06
     benefiting
    0.06
    (vertices
    0.06
     saf
    0.06
     tentative
    0.06
    Den
    0.06
     [_
    0.06
    Act Density 0.021%

    No Known Activations