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

    Neuronpedia

    INDEX
    Explanations

    absolutely, definitely, amazing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nanom
    0.50
     year
    0.50
     hydraz
    0.46
     visa
    0.46
    through
    0.45
     asem
    0.45
     pest
    0.45
     hurdle
    0.45
     tempore
    0.45
     hyphen
    0.45
    POSITIVE LOGITS
     absolutamente
    0.49
     HUGE
    0.48
     абсолютно
    0.48
     Реги
    0.47
    Definitely
    0.47
     assolutamente
    0.46
     AMAZING
    0.46
     Logistics
    0.46
     definitely
    0.45
    Absolutely
    0.45
    Act Density 0.044%

    No Known Activations