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

    Neuronpedia

    INDEX
    Explanations

    digits

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     divorce
    -0.08
    -resource
    -0.07
    -html
    -0.07
    .borrow
    -0.07
    得罪
    -0.06
    ச
    -0.06
    👱
    -0.06
    出台了
    -0.06
    -tra
    -0.06
    _BOOT
    -0.06
    POSITIVE LOGITS
     Orth
    0.08
     Jess
    0.07
    (Category
    0.07
     unequiv
    0.07
    Schedulers
    0.07
    边界
    0.07
    PARATOR
    0.07
    通道
    0.07
     Mag
    0.07
    ninger
    0.07
    Act Density 0.026%

    No Known Activations