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

    Neuronpedia

    INDEX
    Explanations

    acrobatic maneuvers and feats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    1.02
    ام
    0.99
    G
    0.98
    The
    0.97
    ل
    0.96
    ক
    0.88
    h
    0.88
    In
    0.87
    ח
    0.87
    It
    0.85
    POSITIVE LOGITS
    га
    0.85
    ية
    0.77
    jų
    0.73
     еди
    0.68
    üte
    0.64
    ní
    0.64
    üll
    0.64
    ıç
    0.64
     vielf
    0.64
    ü
    0.64
    Act Density 0.001%

    No Known Activations