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

    Neuronpedia

    INDEX
    Explanations

    scientific publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     McDonald
    -0.07
    -,
    -0.06
    たら
    -0.06
     Season
    -0.06
    anford
    -0.06
    ibName
    -0.06
    .Channel
    -0.06
    .HashSet
    -0.06
    _deleted
    -0.06
    enchmark
    -0.06
    POSITIVE LOGITS
     sø
    0.07
     Chip
    0.06
    RELATED
    0.06
     encouraged
    0.06
    шив
    0.06
     References
    0.06
    _STRUCT
    0.06
    自动
    0.06
    _ERRORS
    0.06
    IGENCE
    0.06
    Act Density 0.017%

    No Known Activations