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

    Neuronpedia

    INDEX
    Explanations

    surgical procedures

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Oswald
    -0.08
    :C
    -0.07
     Three
    -0.07
    eldom
    -0.07
    peare
    -0.07
    媒
    -0.06
    /The
    -0.06
    -backed
    -0.06
    几百
    -0.06
     gor
    -0.06
    POSITIVE LOGITS
     아래
    0.07
     patent
    0.07
    (list
    0.07
     Virtual
    0.07
    zone
    0.07
     wik
    0.06
    queued
    0.06
     orig
    0.06
    传统
    0.06
     peppers
    0.06
    Act Density 0.152%

    No Known Activations