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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     approximately
    -0.08
     dollar
    -0.07
     composed
    -0.07
     backgroundColor
    -0.07
    以為
    -0.07
     Rich
    -0.07
    ffi
    -0.07
    依次
    -0.07
     können
    -0.07
    .lat
    -0.07
    POSITIVE LOGITS
    _rewrite
    0.07
    haven
    0.07
     hiếm
    0.07
    远程
    0.07
    jr
    0.07
    _result
    0.07
    莫斯
    0.07
    fds
    0.07
    شف
    0.06
    _cmos
    0.06
    Act Density 0.002%

    No Known Activations