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

    Neuronpedia

    INDEX
    Explanations

    code block terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jedną
    1.23
     thiab
    1.02
     আল্লাহর
    0.99
    WASHINGTON
    0.98
    مانی
    0.97
    ینګ
    0.96
     Zhejiang
    0.96
    ኔታ
    0.95
    ینا
    0.94
    گي
    0.94
    POSITIVE LOGITS
     a
    0.97
     (
    0.85
     in
    0.82
     of
    0.81
    ſ
    0.81
    ;
    0.79
     for
    0.77
    ]$,
    0.77
    ত্বের
    0.75
    (
    0.74
    Act Density 0.243%

    No Known Activations