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

    Neuronpedia

    INDEX
    Explanations

    excellent or good skills

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ä
    1.17
     wana
    1.10
    Ä
    1.00
    trä
    0.99
     än
    0.98
     või
    0.95
     وكل
    0.94
     Dopo
    0.90
     والإ
    0.90
     À
    0.89
    POSITIVE LOGITS
    ність
    1.19
    liness
    1.15
    ساس
    1.14
    速度
    1.09
    ություն
    1.09
     headway
    1.09
     flusso
    1.08
    نش
    1.07
     unison
    1.07
     interpol
    1.03
    Act Density 0.045%

    No Known Activations