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

    Neuronpedia

    INDEX
    Explanations

    child

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     atlas
    -0.06
     eating
    -0.06
    _EOF
    -0.06
     writing
    -0.06
     feats
    -0.06
    ichel
    -0.06
     eat
    -0.06
     Zhou
    -0.06
    이라는
    -0.06
    olut
    -0.05
    POSITIVE LOGITS
     kabil
    0.08
    (++
    0.06
    性
    0.06
     alanı
    0.06
     productList
    0.06
    .offset
    0.06
    .toList
    0.06
    _SECURE
    0.06
    Directed
    0.06
     lz
    0.06
    Act Density 0.033%

    No Known Activations