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
     Demon
    -0.07
     helping
    -0.06
     firsthand
    -0.06
    _STA
    -0.06
     ros
    -0.06
    patches
    -0.06
     Soc
    -0.06
     baff
    -0.06
     Bro
    -0.06
     Мик
    -0.06
    POSITIVE LOGITS
    вен
    0.07
     꼭
    0.07
     inevitable
    0.06
    /*/
    0.06
     [{'
    0.06
     [{"
    0.06
     δύο
    0.06
     Lisp
    0.06
    شود
    0.06
     nelze
    0.06
    Act Density 0.000%

    No Known Activations