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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fortunately
    -0.08
     לצ
    -0.08
     nad
    -0.08
     יהיו
    -0.07
    ுமே
    -0.07
     unfortunately
    -0.07
     вызыва
    -0.07
     Val
    -0.07
     способом
    -0.07
     markup
    -0.07
    POSITIVE LOGITS
     ಬೀ
    0.08
     electric
    0.08
     bolts
    0.07
     backlash
    0.07
     jag
    0.07
     conveyed
    0.07
     strain
    0.07
     Escrit
    0.07
     необходимость
    0.07
     firsthand
    0.07
    Act Density 0.027%

    No Known Activations