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

    Neuronpedia

    INDEX
    Explanations

    say "for"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     המערכת
    -0.07
     Ziel
    -0.07
     מתאים
    -0.07
     השימוש
    -0.07
    侧结构性
    -0.07
    /umd
    -0.07
    廆
    -0.07
     tamanho
    -0.06
     Buildings
    -0.06
     Manufact
    -0.06
    POSITIVE LOGITS
    宣讲
    0.07
    spm
    0.07
    /ip
    0.07
    dragon
    0.07
    .topic
    0.07
    研讨
    0.06
    研讨会
    0.06
     Deferred
    0.06
    _histogram
    0.06
     Gate
    0.06
    Act Density 0.005%

    No Known Activations