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

    Neuronpedia

    INDEX
    Explanations

    foreign language or script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cover
    0.39
     cub
    0.39
     руко
    0.39
    >>
    0.37
     cliff
    0.37
     cm
    0.36
     linea
    0.36
     着
    0.36
     `
    0.36
     kg
    0.35
    POSITIVE LOGITS
    waitUntil
    0.42
    rewsbury
    0.40
     உதாரணமாக
    0.40
     कानूनों
    0.39
     સંદેશ
    0.39
    ன்மையான
    0.39
    νης
    0.39
    葙
    0.39
    ष्टमी
    0.39
     संतुलन
    0.39
    Act Density 0.002%

    No Known Activations