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

    Neuronpedia

    INDEX
    Explanations

    technology

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     medication
    -0.07
    _mot
    -0.07
    comput
    -0.07
    zos
    -0.06
    DO
    -0.06
    Sing
    -0.06
     구글
    -0.06
     двух
    -0.06
    のような
    -0.06
    買
    -0.06
    POSITIVE LOGITS
    арі
    0.07
    arch
    0.06
     tym
    0.06
     uses
    0.06
     typically
    0.06
     factories
    0.06
    μου
    0.06
     mij
    0.06
     dynamic
    0.06
     říj
    0.06
    Act Density 0.018%

    No Known Activations