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

    Neuronpedia

    INDEX
    Explanations

    Mixed languages/codes/numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	ac
    -0.06
    abar
    -0.06
     церк
    -0.06
     supp
    -0.06
    _connector
    -0.06
    _isr
    -0.06
    忠
    -0.06
     Lâm
    -0.06
    ıldı
    -0.06
     unter
    -0.06
    POSITIVE LOGITS
    %)
    0.07
    Registro
    0.06
    듯
    0.06
    here
    0.06
    äh
    0.06
    Flo
    0.06
    good
    0.06
    스는
    0.06
     корист
    0.06
     dispositivo
    0.06
    Act Density 0.006%

    No Known Activations