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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ла
    -0.07
    _login
    -0.07
    (nil
    -0.07
    �로
    -0.07
    _validate
    -0.06
    _marshaled
    -0.06
    ,R
    -0.06
    Over
    -0.06
    اذا
    -0.06
    _,↵
    -0.06
    POSITIVE LOGITS
     rumor
    0.06
    ็บไซต
    0.06
     رسمی
    0.06
     Nội
    0.06
     남자
    0.06
    _traj
    0.06
    _SOFT
    0.06
    uest
    0.06
     Σχ
    0.06
    med
    0.06
    Act Density 0.015%

    No Known Activations