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

    Neuronpedia

    INDEX
    Explanations

    32

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ululo
    -0.09
    California
    -0.08
     Chancellor
    -0.08
    CDD
    -0.08
    Ã
    -0.08
     upgr
    -0.08
     mõju
    -0.08
    ifornia
    -0.08
     подобрать
    -0.08
     Libertadores
    -0.08
    POSITIVE LOGITS
     पर्याप्त
    0.08
     motor
    0.07
     musk
    0.07
     med
    0.07
     tourne
    0.07
     kindness
    0.07
    游
    0.07
     grace
    0.07
     clicks
    0.07
    第一次
    0.07
    Act Density 0.000%

    No Known Activations