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

    Neuronpedia

    INDEX
    Explanations

    committed changes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     it
    0.50
     the
    0.48
     Thanksgiving
    0.46
     underserved
    0.45
     وآ
    0.45
     reliance
    0.44
     lockdowns
    0.43
    登
    0.43
     '
    0.43
     Upt
    0.42
    POSITIVE LOGITS
    imètres
    0.54
    وبة
    0.53
     provincias
    0.52
    ే
    0.50
    رود
    0.50
     imó
    0.49
    icules
    0.48
    uries
    0.48
    Ꮺ
    0.47
    ्युन
    0.46
    Act Density 0.001%

    No Known Activations