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

    Neuronpedia

    INDEX
    Explanations

    as something happened

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     maar
    1.05
     pero
    1.04
     but
    1.00
    .'
    1.00
    。.
    0.99
    。
    0.98
    。\
    0.93
     mutta
    0.93
    .\
    0.91
     tetapi
    0.90
    POSITIVE LOGITS
    ជាមួយនឹង
    0.78
    และความ
    0.71
     devoid
    0.70
     surrounded
    0.69
     Surrounded
    0.68
     decked
    0.66
     amidst
    0.66
    faced
    0.63
     بجائے
    0.61
     Released
    0.61
    Act Density 0.079%

    No Known Activations