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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     solving
    -0.08
     verify
    -0.08
     intuit
    -0.08
    一本
    -0.07
     predict
    -0.07
     formulas
    -0.07
     functioning
    -0.07
     performed
    -0.07
     iron
    -0.07
     funcion
    -0.07
    POSITIVE LOGITS
     ആഘ
    0.09
     कृष
    0.09
     cardigan
    0.09
     ɔ
    0.09
     חג
    0.08
     подел
    0.08
     الجمعة
    0.08
     സംഘം
    0.08
     haɗ
    0.08
     zor
    0.08
    Act Density 0.012%

    No Known Activations