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

    Neuronpedia

    INDEX
    Explanations

    official sources reporting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hoặc
    0.45
    =
    0.37
     yoki
    0.37
     veya
    0.36
     babies
    0.36
    可能会
    0.35
     unités
    0.34
     value
    0.34
     horsepower
    0.34
     bitmaps
    0.33
    POSITIVE LOGITS
     periodistas
    0.49
     сообщил
    0.49
     spokesman
    0.48
     вчера
    0.45
     spokesperson
    0.44
     briefing
    0.44
     корреспонд
    0.43
     portavoz
    0.43
    他說
    0.43
     spokeswoman
    0.42
    Act Density 0.020%

    No Known Activations