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

    Neuronpedia

    INDEX
    Explanations

    java spring framework

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝘴
    0.80
    ס
    0.79
    ਣ
    0.73
    mosquito
    0.71
    ة
    0.71
    sembl
    0.70
    ACT
    0.68
    ੋਰ
    0.68
    は
    0.67
    な
    0.67
    POSITIVE LOGITS
     drew
    0.71
     ৪
    0.68
     threw
    0.67
     prayed
    0.66
     weren
    0.63
     drank
    0.63
     shov
    0.63
     ១
    0.63
     ٣
    0.62
     automaker
    0.61
    Act Density 0.000%

    No Known Activations