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

    Neuronpedia

    INDEX
    Explanations

    forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ulado
    -0.08
     diferentes
    -0.07
     banco
    -0.07
     همه
    -0.06
    Cb
    -0.06
     DirectoryInfo
    -0.06
    ponde
    -0.06
    wm
    -0.06
     Lemma
    -0.06
    DNS
    -0.06
    POSITIVE LOGITS
    =-=-=-=-
    0.08
     〃
    0.07
    內
    0.06
     ZX
    0.06
     お
    0.06
    、一
    0.06
    、お
    0.06
    {(
    0.06
    Ан
    0.06
    ลาย
    0.06
    Act Density 0.023%

    No Known Activations