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

    Neuronpedia

    INDEX
    Explanations

    commands and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nova
    0.50
    REGIUNE
    0.46
     ivvu
    0.45
     lemons
    0.44
    ;//
    0.44
    quali
    0.44
    hesize
    0.43
    desired
    0.43
    ндекс
    0.43
    едера
    0.42
    POSITIVE LOGITS
     gdy
    0.46
     jazdy
    0.44
     pracy
    0.42
     Roads
    0.42
     Words
    0.41
    تمل
    0.41
     létre
    0.41
     Wake
    0.41
    Crossing
    0.41
     Victims
    0.41
    Act Density 0.002%

    No Known Activations