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

    Neuronpedia

    INDEX
    Explanations

    Ra

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     способом
    -0.06
     zn
    -0.06
     ("%
    -0.06
     Wasser
    -0.06
     feast
    -0.05
     lowercase
    -0.05
    Pic
    -0.05
    _fl
    -0.05
     thủ
    -0.05
    (Module
    -0.05
    POSITIVE LOGITS
    RA
    0.07
     DA
    0.07
     corro
    0.07
     rgba
    0.07
     germ
    0.06
    aje
    0.06
     خود
    0.06
     BRA
    0.06
    τα
    0.06
     entra
    0.06
    Act Density 0.008%

    No Known Activations