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

    Neuronpedia

    INDEX
    Explanations

    random noise

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    룺
    0.41
    리티
    0.40
     און
    0.39
     specs
    0.36
     temptations
    0.36
    ängel
    0.36
     }=
    0.35
     rations
    0.35
     کوډ
    0.35
    퍁
    0.34
    POSITIVE LOGITS
    What
    0.57
    Q
    0.52
    How
    0.48
    When
    0.47
     What
    0.46
    One
    0.46
    ---
    0.46
    The
    0.45
     what
    0.43
    There
    0.42
    Act Density 0.000%

    No Known Activations