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

    Neuronpedia

    INDEX
    Explanations

    operation followed by a name

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     grass
    1.78
    ০০
    1.77
    인
    1.73
    टर
    1.64
    ro
    1.63
    乇
    1.63
    ানি
    1.56
     fascinating
    1.56
    ಿಕೆ
    1.56
     renewed
    1.55
    POSITIVE LOGITS
    ى
    2.63
    ون
    2.02
    ی
    2.00
     opérations
    1.99
    ną
    1.95
     conjunta
    1.93
    يين
    1.91
     achats
    1.91
    a
    1.86
    ROAD
    1.85
    Act Density 0.017%

    No Known Activations