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

    Neuronpedia

    INDEX
    Explanations

    code syntax elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Celsius
    1.85
     derece
    1.84
     уж
    1.68
     सेल्सियस
    1.66
    ि
    1.64
    нное
    1.64
    BTW
    1.58
     Fahrenheit
    1.57
    ोदर
    1.54
     качества
    1.54
    POSITIVE LOGITS
    ק
    1.61
    mathop
    1.56
    ்க
    1.46
    ム
    1.45
    ле
    1.44
    זו
    1.44
     définit
    1.43
    कर्ता
    1.36
    lbrace
    1.34
     vole
    1.34
    Act Density 0.026%

    No Known Activations