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

    Neuronpedia

    INDEX
    Explanations

    Measurement, Bag, collected

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mumbai
    0.47
     Irving
    0.44
     সহজেই
    0.44
     Caffeine
    0.43
    ATTRIBUTE
    0.42
     irrit
    0.41
    肚
    0.40
    动力
    0.40
     mattresses
    0.40
    ⿶
    0.40
    POSITIVE LOGITS
    on
    0.46
    as
    0.44
     gì
    0.43
    /
    0.43
     året
    0.41
    res
    0.40
    until
    0.39
    an
    0.39
    eren
    0.39
    Didn
    0.39
    Act Density 0.019%

    No Known Activations