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

    Neuronpedia

    INDEX
    Explanations

    break of character

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     students
    0.78
     κάθε
    0.76
     people
    0.75
     talented
    0.74
     impeccable
    0.73
     rookies
    0.72
     your
    0.72
     vertebrae
    0.72
     everyone
    0.71
     můžete
    0.70
    POSITIVE LOGITS
    のが
    0.64
    Ambient
    0.64
    Deferred
    0.61
    С
    0.61
    Е
    0.60
    dengan
    0.58
    Criminal
    0.58
    Т
    0.58
    Ч
    0.57
    Custom
    0.57
    Act Density 10.554%

    No Known Activations