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

    Neuronpedia

    INDEX
    Explanations

    check questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ras
    0.50
    او
    0.46
    ాలు
    0.46
    Anonymous
    0.45
    कि
    0.45
    Br
    0.45
    Ak
    0.45
    errno
    0.44
    श्र
    0.44
    Would
    0.44
    POSITIVE LOGITS
     Dyed
    0.47
     immunological
    0.45
     scoring
    0.43
     dynamism
    0.43
     morphological
    0.43
     继续
    0.42
     mechanistic
    0.42
     Proceeds
    0.42
     Ally
    0.41
     ಅಭಿಮಾನ
    0.41
    Act Density 0.001%

    No Known Activations