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

    Neuronpedia

    INDEX
    Explanations

    scale massive volume

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     এবং
    0.79
    었고
    0.72
     և
    0.70
     however
    0.70
     and
    0.68
     и
    0.67
     azonban
    0.67
    തും
    0.66
     και
    0.65
    했고
    0.65
    POSITIVE LOGITS
    ńsk
    0.55
    最重要的
    0.54
     travaillons
    0.54
    retryWrites
    0.54
     patriotism
    0.54
     ;-)
    0.54
     paura
    0.53
     crucially
    0.53
     activism
    0.53
     censoring
    0.53
    Act Density 0.000%

    No Known Activations