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

    Neuronpedia

    INDEX
    Explanations

    quantities and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Cols
    0.73
    Suffix
    0.73
    Benzyloxy
    0.72
    Quant
    0.70
    Ratio
    0.69
    Minute
    0.67
    Delimiter
    0.67
    Bankruptcy
    0.67
    Aspect
    0.65
    itiert
    0.65
    POSITIVE LOGITS
     depending
    1.54
     Depending
    1.32
     total
    1.13
    depending
    1.12
     pure
    1.06
    左右
    1.05
     dependiendo
    1.05
     minimum
    1.03
     plus
    1.03
    Depending
    1.01
    Act Density 0.628%

    No Known Activations