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

    Neuronpedia

    INDEX
    Explanations

    deadlifts, dead bugs, deadpan

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ه
    2.47
     inconvenience
    2.08
     pamoja
    2.02
    ী
    2.00
    ా
    1.89
    ية
    1.81
    ে
    1.81
    ہ
    1.80
    هههه
    1.78
    ν
    1.73
    POSITIVE LOGITS
    IAN
    2.23
    IST
    1.98
    ا
    1.84
    AKE
    1.84
    AA
    1.80
    ಒ
    1.77
    IQUE
    1.75
    ALITY
    1.74
    ILL
    1.72
    可以
    1.71
    Act Density 0.002%

    No Known Activations