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

    Neuronpedia

    INDEX
    Explanations

    =@

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Counter
    -0.06
     Burgess
    -0.06
     Men
    -0.06
    ……↵↵
    -0.06
     debunk
    -0.06
     Kim
    -0.06
    Kim
    -0.06
     Chen
    -0.06
     fon
    -0.06
    NonNull
    -0.06
    POSITIVE LOGITS
    (m
    0.07
     gly
    0.07
     Initi
    0.06
     OF
    0.06
     artworks
    0.06
    (mm
    0.06
    .Hit
    0.06
    LM
    0.06
     LINEAR
    0.06
    _location
    0.06
    Act Density 0.001%

    No Known Activations