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

    Neuronpedia

    INDEX
    Explanations

    needs more information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xda
    -0.07
    .invalidate
    -0.07
     estilo
    -0.07
    enabled
    -0.07
     podmínky
    -0.07
    dato
    -0.07
     günü
    -0.07
     BAS
    -0.07
    固定
    -0.07
     bureauc
    -0.06
    POSITIVE LOGITS
    (fe
    0.06
     договор
    0.06
     ep
    0.06
    }">↵
    0.06
     jig
    0.06
    (Op
    0.06
     {-
    0.06
    Ав
    0.06
     Dmit
    0.06
    crease
    0.05
    Act Density 0.021%

    No Known Activations