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

    Neuronpedia

    INDEX
    Explanations

    avoid legal trouble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     willfully
    0.49
    ੂੰ
    0.47
    acters
    0.46
    𝘄
    0.45
    кті
    0.45
    ヒト
    0.44
    ㄽ
    0.44
    sthresh
    0.43
    ких
    0.43
    ті
    0.43
    POSITIVE LOGITS
     Personality
    0.42
     तुमच्या
    0.40
     Psychology
    0.39
    }}}{
    0.39
     udě
    0.38
     chassis
    0.38
     Styles
    0.38
    *
    0.38
     receiver
    0.37
    Phantom
    0.37
    Act Density 0.006%

    No Known Activations