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

    Neuronpedia

    INDEX
    Explanations

    limits and danger

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Ih
    -0.09
     kis
    -0.08
    .pull
    -0.08
    KI
    -0.08
     Pig
    -0.08
     Kis
    -0.08
     reass
    -0.08
     cloning
    -0.08
     RGB
    -0.08
    iddish
    -0.07
    POSITIVE LOGITS
     defendant
    0.10
     plaintiff
    0.10
     unequiv
    0.09
     обстоятель
    0.09
     Plaintiff
    0.09
     warrant
    0.09
     circumstances
    0.09
     يجوز
    0.09
     ನ್ಯಾಯ
    0.09
     looph
    0.09
    Act Density 0.110%

    No Known Activations