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

    Neuronpedia

    INDEX
    Explanations

    toxins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    tg
    -0.07
    inary
    -0.07
     Tony
    -0.07
    etas
    -0.07
    YS
    -0.06
     RPC
    -0.06
    oined
    -0.06
    INARY
    -0.06
    رده
    -0.06
     consolation
    -0.06
    POSITIVE LOGITS
    Semantic
    0.07
    ความค
    0.06
     Belediyesi
    0.06
     چنان
    0.06
     coloring
    0.06
     elected
    0.06
     참
    0.06
    (encoder
    0.06
    lectual
    0.06
     click
    0.06
    Act Density 0.006%

    No Known Activations