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

    Neuronpedia

    INDEX
    Explanations

    pieces

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     welcomed
    -0.07
    ору
    -0.06
     scriptures
    -0.06
    โพ
    -0.06
     amacı
    -0.06
     빛
    -0.06
     Vogue
    -0.06
    Billy
    -0.06
    .pull
    -0.06
     özellikleri
    -0.06
    POSITIVE LOGITS
     pieces
    0.08
    olate
    0.07
    _DA
    0.07
     dapat
    0.07
    Pieces
    0.07
     pottery
    0.07
     disparate
    0.06
    .dest
    0.06
    igsaw
    0.06
    199
    0.06
    Act Density 0.012%

    No Known Activations