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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    FINITE
    -0.07
     відом
    -0.07
    .proj
    -0.07
    MSG
    -0.07
    copy
    -0.06
     Testament
    -0.06
    patrick
    -0.06
    Van
    -0.06
    くる
    -0.06
    xFC
    -0.06
    POSITIVE LOGITS
     kraje
    0.07
     congress
    0.06
    (article
    0.06
     looking
    0.06
    ellidos
    0.05
     у
    0.05
    OUGH
    0.05
     gateway
    0.05
    =document
    0.05
    دة
    0.05
    Act Density 0.005%

    No Known Activations