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

    Neuronpedia

    INDEX
    Explanations

    Pokemon Gym Leaders/lists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     instincts
    -0.09
     extinct
    -0.08
    kb
    -0.08
    _sort
    -0.08
     удоб
    -0.08
     anguish
    -0.08
     romp
    -0.08
     lovable
    -0.08
     ease
    -0.08
     instantiate
    -0.08
    POSITIVE LOGITS
    preuves
    0.08
    راكز
    0.08
    vio
    0.08
    Passwords
    0.08
     yritt
    0.07
     talleres
    0.07
    ulis
    0.07
    Publ
    0.07
    urangan
    0.07
    atham
    0.07
    Act Density 0.006%

    No Known Activations