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

    Neuronpedia

    INDEX
    Explanations

    principle

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Apart
    0.63
    ရော
    0.61
     Sasha
    0.59
     alamy
    0.59
     FIGHT
    0.59
    ieger
    0.59
     fighting
    0.59
    fighting
    0.58
    atae
    0.57
     Mabel
    0.57
    POSITIVE LOGITS
     principles
    0.61
     prinsip
    0.61
    principles
    0.57
     तत्वा
    0.54
     Principles
    0.54
    Principles
    0.54
     principle
    0.53
    URATION
    0.52
    PRINC
    0.52
    த்திற்கு
    0.52
    Act Density 0.000%

    No Known Activations