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

    Neuronpedia

    INDEX
    Explanations

    machine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    urv
    -0.07
     Atatürk
    -0.07
     nhé
    -0.07
     Flux
    -0.06
     pretrained
    -0.06
    Arena
    -0.06
    ुभव
    -0.06
    enaire
    -0.06
    alker
    -0.06
     evet
    -0.06
    POSITIVE LOGITS
     forget
    0.06
     viewing
    0.06
     neces
    0.06
    stitution
    0.06
     printer
    0.05
     tells
    0.05
     ci
    0.05
     tekn
    0.05
     uluslararası
    0.05
     electronic
    0.05
    Act Density 0.011%

    No Known Activations