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

    Neuronpedia

    INDEX
    Explanations

    xmlns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вар
    -0.06
     المس
    -0.06
     田
    -0.06
    스티
    -0.06
     Kil
    -0.06
     진행
    -0.06
     Adoles
    -0.06
     HDD
    -0.06
    Lake
    -0.06
    يب
    -0.06
    POSITIVE LOGITS
    .keyboard
    0.07
    (ERR
    0.07
    partners
    0.07
     Não
    0.07
    íše
    0.06
    *S
    0.06
     appeared
    0.06
     Behavioral
    0.06
    Indexed
    0.06
    睡
    0.06
    Act Density 0.001%

    No Known Activations