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

    Neuronpedia

    INDEX
    Explanations

    raw eggs safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mix
    -0.07
     waste
    -0.07
     buri
    -0.07
     regular
    -0.07
     achievements
    -0.07
     direction
    -0.07
     Bari
    -0.07
    .Rotate
    -0.07
    direction
    -0.07
     logarith
    -0.07
    POSITIVE LOGITS
     təhlük
    0.12
     қауіп
    0.12
    风险
    0.12
    安全
    0.12
     turvall
    0.12
     безопасность
    0.12
     안전
    0.12
     பாதுக
    0.11
     safety
    0.11
     Safety
    0.11
    Act Density 0.007%

    No Known Activations