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

    Neuronpedia

    INDEX
    Explanations

    diagnosis codes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ray
    -0.07
     Kirst
    -0.07
     dor
    -0.07
     pedigree
    -0.07
    etect
    -0.07
     torchvision
    -0.07
     Fitz
    -0.07
     irm
    -0.07
     ciudad
    -0.06
     Viking
    -0.06
    POSITIVE LOGITS
    0.08
    _LAST
    0.07
    nodoc
    0.07
     Going
    0.07
    סחר
    0.07
    arbeit
    0.07
    렌
    0.06
     משת
    0.06
    [self
    0.06
     automobile
    0.06
    Act Density 0.002%

    No Known Activations