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

    Neuronpedia

    INDEX
    Explanations

    Transliterations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mecanismo
    -0.10
     caratter
    -0.09
    ателям
    -0.08
     Capitals
    -0.08
    наки
    -0.08
    سسة
    -0.08
    ottest
    -0.08
     Include
    -0.08
    атель
    -0.08
     Making
    -0.08
    POSITIVE LOGITS
     μό
    0.07
    ૉ
    0.07
    лай
    0.07
     FOB
    0.07
    umulator
    0.07
    ส์
    0.07
     та
    0.07
     hun
    0.07
     кей
    0.07
     verändert
    0.07
    Act Density 0.041%

    No Known Activations