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

    Neuronpedia

    INDEX
    Explanations

    level and balance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     legitim
    0.78
     invalid
    0.75
    খণ্ড
    0.72
     Validity
    0.68
     একত্রিত
    0.67
     изоли
    0.67
    дентифика
    0.66
     அழக
    0.66
     speciali
    0.65
    izarre
    0.65
    POSITIVE LOGITS
     level
    1.69
    level
    1.58
    ระดับ
    1.58
     degree
    1.56
     amount
    1.54
    Amount
    1.51
    degree
    1.50
    Level
    1.46
     Amount
    1.46
     уровень
    1.43
    Act Density 0.264%

    No Known Activations