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

    Neuronpedia

    INDEX
    Explanations

    foreign words and homeowner context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     to
    0.47
    sPath
    0.47
    s
    0.45
     کچھ
    0.44
     coats
    0.44
     cultures
    0.43
     často
    0.43
     shades
    0.42
    ン
    0.42
     spécifiques
    0.42
    POSITIVE LOGITS
    റേ
    0.44
     !$
    0.43
    作った
    0.42
    傭
    0.41
     официально
    0.40
     बेशक
    0.39
     kazi
    0.39
     judgmental
    0.38
    假的
    0.38
     setUser
    0.38
    Act Density 0.010%

    No Known Activations