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

    Neuronpedia

    INDEX
    Explanations

    German compound noun roots

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     लहान
    0.35
     المثلثيه
    0.35
     SUSY
    0.35
     एगो
    0.33
     Пусть
    0.33
     मोठी
    0.33
     otherworldly
    0.32
     जहां
    0.31
     forested
    0.31
     മികച്ച
    0.31
    POSITIVE LOGITS
    serie
    0.45
    status
    0.44
    ver
    0.42
    proble
    0.42
    v
    0.41
    ss
    0.41
    ma
    0.41
    sp
    0.40
    gruppen
    0.40
    klassen
    0.40
    Act Density 0.014%

    No Known Activations