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

    Neuronpedia

    INDEX
    Explanations

    learning for apps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     momentary
    0.97
     supernatural
    0.92
     Pikachu
    0.90
    tdown
    0.90
    waard
    0.87
    ்சைடு
    0.83
    textbox
    0.83
     shaky
    0.82
    κος
    0.81
    owany
    0.79
    POSITIVE LOGITS
    o
    1.27
    ه
    1.21
    ம்
    1.18
    扞
    1.15
    ال
    1.15
    DU
    1.13
    الإ
    1.11
    转换
    1.10
     ಅನ್ನ
    1.08
    म
    1.08
    Act Density 0.000%

    No Known Activations