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

    Neuronpedia

    INDEX
    Explanations

    say ".system"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    تخذ
    -0.07
    county
    -0.07
    业
    -0.07
    这条
    -0.07
    似乎是
    -0.07
    鹴
    -0.07
    (nullable
    -0.06
     pParent
    -0.06
     Responsible
    -0.06
     TResult
    -0.06
    POSITIVE LOGITS
    "{
    0.07
     Bair
    0.07
    תחושה
    0.07
    チャー
    0.06
    ]/
    0.06
    icia
    0.06
     Gladiator
    0.06
    .geom
    0.06
    ";
↵
    0.06
    威海
    0.06
    Act Density 0.000%

    No Known Activations