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

    Neuronpedia

    INDEX
    Explanations

    MEMS and things that are scary

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stress
    -0.98
     STRESS
    -0.88
    Stress
    -0.85
     Stress
    -0.84
     stressed
    -0.74
    stress
    -0.71
     scare
    -0.69
     scary
    -0.65
    stressed
    -0.65
    ,:),
    -0.63
    POSITIVE LOGITS
    s
    0.79
     onCancelled
    0.67
    ingly
    0.63
    sing
    0.60
    ful
    0.58
    GEBURTSDATUM
    0.58
     InputDecoration
    0.57
    IsContent
    0.57
    tvguidetime
    0.56
     فريبيس
    0.56
    Act Density 0.439%

    No Known Activations