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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ucket
    -0.07
    Football
    -0.07
     getMax
    -0.07
    :w
    -0.06
    -ф
    -0.06
    .Class
    -0.06
     brown
    -0.06
     bor
    -0.06
    'ét
    -0.06
    Jos
    -0.06
    POSITIVE LOGITS
    ):↵
    0.07
     nextProps
    0.07
    에서의
    0.06
    ्बन
    0.06
    quota
    0.06
     دهه
    0.06
     Kanun
    0.06
    haust
    0.06
    .userInteractionEnabled
    0.06
     ruk
    0.06
    Act Density 0.060%

    No Known Activations