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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Street
    -0.06
    esto
    -0.06
     sands
    -0.06
    /search
    -0.06
    Fitness
    -0.06
    ﺪ
    -0.06
     FX
    -0.06
    ALSE
    -0.06
     الزر
    -0.05
    guns
    -0.05
    POSITIVE LOGITS
     �
    0.07
    .GetItem
    0.07
     distract
    0.07
    (ar
    0.07
     trig
    0.07
     강
    0.07
     renamed
    0.07
     Gonz
    0.07
     Syracuse
    0.06
    らない
    0.06
    Act Density 0.063%

    No Known Activations