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

    Neuronpedia

    INDEX
    Explanations

    meta

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Surgical
    -0.07
     Univ
    -0.07
     worm
    -0.06
     Select
    -0.06
    (Network
    -0.06
    xeb
    -0.06
    .vocab
    -0.06
     reform
    -0.06
    laus
    -0.06
    button
    -0.06
    POSITIVE LOGITS
     remote
    0.06
    ـل
    0.06
    قل
    0.06
    _ttl
    0.06
     gốc
    0.06
     женщины
    0.06
    �
    0.06
     앉
    0.06
     healthy
    0.06
     bouts
    0.06
    Act Density 0.003%

    No Known Activations