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

    Neuronpedia

    INDEX
    Explanations

    send

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cater
    -0.07
     مق
    -0.06
    Bullet
    -0.06
     shady
    -0.06
    デ
    -0.06
    Row
    -0.06
    Last
    -0.06
     observation
    -0.06
    _CURSOR
    -0.06
    .WARNING
    -0.05
    POSITIVE LOGITS
    chlor
    0.07
    ез
    0.06
     spinal
    0.06
    nier
    0.06
     důležité
    0.06
    -plugins
    0.06
     hurt
    0.06
     diferente
    0.06
    .AddSingleton
    0.06
    iná
    0.06
    Act Density 0.016%

    No Known Activations