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

    Neuronpedia

    INDEX
    Explanations

    charge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    森
    -0.08
    सर
    -0.07
     هفت
    -0.06
     آی
    -0.06
    姉
    -0.06
     항
    -0.06
     underwear
    -0.06
     càng
    -0.06
    Cake
    -0.06
    アイ
    -0.06
    POSITIVE LOGITS
    ;",
    0.07
    ).(
    0.07
     mocked
    0.07
    (number
    0.06
    _charge
    0.06
    egra
    0.06
     residues
    0.06
    idue
    0.06
     ims
    0.06
     натураль
    0.06
    Act Density 0.003%

    No Known Activations