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

    Neuronpedia

    INDEX
    Explanations

    come

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Inputs
    -0.07
    There
    -0.07
     Brothers
    -0.07
     livro
    -0.06
    (plot
    -0.06
     Т
    -0.06
     diplomat
    -0.06
     为
    -0.06
    iesz
    -0.06
    Lord
    -0.06
    POSITIVE LOGITS
    _accel
    0.07
     analyzer
    0.06
     BaseController
    0.06
     ecc
    0.06
     المخت
    0.06
     generations
    0.06
     月
    0.06
    ataires
    0.06
    ผล
    0.06
    AUD
    0.06
    Act Density 0.015%

    No Known Activations