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

    Neuronpedia

    INDEX
    Explanations

    diagnose

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Large
    -0.07
     hor
    -0.07
     City
    -0.06
    .Euler
    -0.06
     Mario
    -0.06
    教
    -0.06
     REC
    -0.06
    .NotFound
    -0.06
    ampion
    -0.06
    _SR
    -0.06
    POSITIVE LOGITS
     LIMITED
    0.06
    .Multi
    0.06
     domin
    0.06
     διά
    0.06
    atura
    0.06
     สพ
    0.06
     inhab
    0.06
    Multiple
    0.06
    нії
    0.06
    延
    0.06
    Act Density 0.004%

    No Known Activations