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

    Neuronpedia

    INDEX
    Explanations

    technical/scientific topics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -width
    -0.08
    ocos
    -0.07
     LARGE
    -0.07
     consecutive
    -0.07
     shave
    -0.07
    kw
    -0.06
    命
    -0.06
    าร
    -0.06
    好看
    -0.06
     Whites
    -0.06
    POSITIVE LOGITS
    ................................
    0.07
    거리
    0.07
     Iceland
    0.07
     costo
    0.07
     giả
    0.07
    胸前
    0.07
    🀄
    0.07
     الأجنبية
    0.06
    Ped
    0.06
     الأمريكية
    0.06
    Act Density 1.802%

    No Known Activations