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

    Neuronpedia

    INDEX
    Explanations

    Black hole singularities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    strcasecmp
    -0.08
     Tone
    -0.08
     surveys
    -0.07
    Tone
    -0.07
    xx
    -0.07
     tone
    -0.07
     autot
    -0.07
    dr
    -0.07
    rotate
    -0.07
     Survey
    -0.07
    POSITIVE LOGITS
     singular
    0.13
     Singular
    0.12
     النهاية
    0.10
    毁
    0.10
     inaccessible
    0.09
     explosions
    0.09
     نقطة
    0.09
     extinction
    0.09
     catastrophe
    0.09
     ошибки
    0.09
    Act Density 0.002%

    No Known Activations