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

    Neuronpedia

    INDEX
    Explanations

    span

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    했다
    -0.06
    Clo
    -0.06
     ikea
    -0.06
    Certain
    -0.06
    GRESS
    -0.06
     scram
    -0.06
    dued
    -0.06
    .Gray
    -0.06
    For
    -0.06
    softmax
    -0.06
    POSITIVE LOGITS
    _fake
    0.07
     CPI
    0.07
     XO
    0.06
     convoy
    0.06
     incarcerated
    0.06
    upid
    0.06
     fat
    0.06
     hearing
    0.06
     (?)
    0.06
     stupid
    0.06
    Act Density 0.000%

    No Known Activations