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

    Neuronpedia

    INDEX
    Explanations

    experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    2.58
    2.08
    ol
    1.97
    ain
    1.94
    ed
    1.93
    ag
    1.91
     essentielles
    1.90
    ated
    1.87
    с
    1.84
    ন
    1.80
    POSITIVE LOGITS
    जन्य
    2.13
    IamPermissions
    2.05
    ㇂
    2.05
    Ｃ
    1.95
    𝓻
    1.94
    Chloro
    1.90
     Elaina
    1.90
     ＊
    1.88
    iencia
    1.85
    Experiences
    1.84
    Act Density 0.123%

    No Known Activations