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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Iso
    -0.07
     "}\
    -0.07
    udad
    -0.07
    ament
    -0.06
     editors
    -0.06
    warning
    -0.06
    .docs
    -0.06
    nown
    -0.06
    <Course
    -0.06
    ainment
    -0.06
    POSITIVE LOGITS
     hải
    0.06
    韩
    0.06
     diss
    0.06
    _mv
    0.06
     Alonso
    0.06
     пев
    0.05
    ProgressBar
    0.05
    esses
    0.05
    _oct
    0.05
    _REFERER
    0.05
    Act Density 0.142%

    No Known Activations