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

    Neuronpedia

    INDEX
    Explanations

    clinical

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    реть
    -0.06
     sonst
    -0.06
    lfw
    -0.06
    .AspNet
    -0.06
    ندق
    -0.06
     Wikispecies
    -0.06
    pto
    -0.06
     мног
    -0.06
     Banco
    -0.06
    $"
    -0.06
    POSITIVE LOGITS
    48
    0.07
    Medium
    0.07
    (non
    0.07
    (Message
    0.06
     discern
    0.06
    images
    0.06
    .hr
    0.06
     sosyal
    0.06
     bát
    0.06
     gradual
    0.06
    Act Density 0.001%

    No Known Activations