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

    Neuronpedia

    INDEX
    Explanations

    topics about change and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     parte
    0.69
    irms
    0.67
     latéraux
    0.62
     لینے
    0.62
     बनाने
    0.60
    ówno
    0.59
     اداروں
    0.58
     öner
    0.58
    rzeć
    0.58
    ంక
    0.57
    POSITIVE LOGITS
     pace
    0.96
     aftermath
    0.87
     dawn
    0.86
     fight
    0.85
     onslaught
    0.84
     advent
    0.84
     rise
    0.83
     tide
    0.82
     outlook
    0.82
     pandemic
    0.81
    Act Density 0.237%

    No Known Activations