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

    Neuronpedia

    INDEX
    Explanations

    formal/technical writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Runtime
    -0.08
    (element
    -0.07
    辇
    -0.07
     Quickly
    -0.07
    אזרח
    -0.07
     obedient
    -0.06
     softer
    -0.06
    pdf
    -0.06
     tüm
    -0.06
    =date
    -0.06
    POSITIVE LOGITS
    改造
    0.07
    цион
    0.07
    �
    0.07
    Θ
    0.07
    豁
    0.07
    _IV
    0.07
     العالمي
    0.06
    รา
    0.06
    Ra
    0.06
     Deg
    0.06
    Act Density 0.009%

    No Known Activations