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

    Neuronpedia

    INDEX
    Explanations

    ys

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tie
    -0.07
     picnic
    -0.06
    parator
    -0.06
    (act
    -0.06
    חיבור
    -0.06
    _has
    -0.06
    ATEGY
    -0.06
    拓展
    -0.06
    飞扬
    -0.06
     Feinstein
    -0.06
    POSITIVE LOGITS
     Allow
    0.07
    忘れ
    0.07
     unlocked
    0.07
     helmet
    0.07
    .column
    0.07
     internally
    0.06
    שמים
    0.06
    .Course
    0.06
    了我的
    0.06
    .Res
    0.06
    Act Density 0.000%

    No Known Activations