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

    Neuronpedia

    INDEX
    Explanations

    order of importance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Taylor
    -0.07
    ,item
    -0.07
     penalty
    -0.07
     franc
    -0.07
    ывать
    -0.06
    (ang
    -0.06
     exhibit
    -0.06
     Sanctuary
    -0.06
    shore
    -0.06
     surfaces
    -0.06
    POSITIVE LOGITS
    .ec
    0.07
    .keep
    0.06
    _quantity
    0.06
    reesome
    0.06
     питання
    0.06
     orbs
    0.06
     ecc
    0.05
     nového
    0.05
     Continue
    0.05
    (path
    0.05
    Act Density 0.019%

    No Known Activations