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

    Neuronpedia

    INDEX
    Explanations

    geometry problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    obox
    -0.09
    .attrs
    -0.08
    주
    -0.08
    되
    -0.07
     sociais
    -0.07
    다고
    -0.07
    868
    -0.07
    	ID
    -0.07
     호
    -0.07
     scrutin
    -0.07
    POSITIVE LOGITS
     בשביל
    0.10
     diagonal
    0.09
     मार्ग
    0.09
     zig
    0.09
     Shortcut
    0.09
     फिर
    0.09
     прогул
    0.09
    straight
    0.09
     schoon
    0.08
     попасть
    0.08
    Act Density 0.015%

    No Known Activations