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

    Neuronpedia

    INDEX
    Explanations

    further

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     теперь
    -0.07
     Rao
    -0.06
    widgets
    -0.06
    ring
    -0.06
     زمین
    -0.06
    ertino
    -0.06
    它
    -0.06
    (obj
    -0.06
     ((!
    -0.06
     rằng
    -0.06
    POSITIVE LOGITS
     further
    0.09
     fermentation
    0.07
    CV
    0.07
    42
    0.06
     giver
    0.06
    739
    0.06
    .UN
    0.06
     Atatürk
    0.06
     persever
    0.06
     presenter
    0.06
    Act Density 0.017%

    No Known Activations