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

    Neuronpedia

    INDEX
    Explanations

    geometric reflection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     USING
    -0.09
     revisions
    -0.08
    /environment
    -0.08
    ukat
    -0.08
     distinctive
    -0.07
     citation
    -0.07
     vit
    -0.07
     maths
    -0.07
     باستخدام
    -0.07
    iffy
    -0.07
    POSITIVE LOGITS
     termed
    0.08
     Lap
    0.08
    ர்கள்
    0.07
    Lap
    0.07
    Lucas
    0.07
    onstruk
    0.07
     caer
    0.07
     enri
    0.07
     雷
    0.07
     ther
    0.07
    Act Density 0.005%

    No Known Activations