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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kdyby
    -0.06
    ectl
    -0.06
     dosud
    -0.06
     stripe
    -0.06
     besie
    -0.06
    larını
    -0.06
    ském
    -0.06
    ตรว
    -0.06
    clientes
    -0.06
    стві
    -0.06
    POSITIVE LOGITS
    (rot
    0.07
     divis
    0.07
     Quit
    0.07
     decay
    0.07
     degradation
    0.07
    ,K
    0.07
    Read
    0.07
     оказ
    0.07
     Lo
    0.07
    .re
    0.07
    Act Density 0.037%

    No Known Activations