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

    Neuronpedia

    INDEX
    Explanations

    injuries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    second
    -0.07
    ma
    -0.06
    	stats
    -0.06
     título
    -0.06
     합니다
    -0.06
     Alma
    -0.06
     Karen
    -0.06
     morality
    -0.06
    sp
    -0.06
    نم
    -0.06
    POSITIVE LOGITS
    _launcher
    0.07
    0.06
    EqualityComparer
    0.06
     bị
    0.06
    .**************↵
    0.06
     cleric
    0.06
     Sect
    0.06
     Tribunal
    0.06
    StartupScript
    0.06
    减
    0.06
    Act Density 0.191%

    No Known Activations