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

    Neuronpedia

    INDEX
    Explanations

    key-value store

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    'all
    -0.06
     vysoké
    -0.06
    Lab
    -0.06
    139
    -0.06
    ακ
    -0.06
     Tuy
    -0.06
    icides
    -0.06
     guard
    -0.06
     cualquier
    -0.06
     Exp
    -0.06
    POSITIVE LOGITS
    ushi
    0.07
    spiel
    0.06
     storytelling
    0.06
     abnormal
    0.06
     indian
    0.06
    達
    0.06
     mildly
    0.06
     imgs
    0.06
    (argument
    0.06
    (updated
    0.06
    Act Density 0.019%

    No Known Activations