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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    awy
    -0.07
    -स
    -0.07
     celebrated
    -0.07
    Presentation
    -0.06
    ram
    -0.06
     screwed
    -0.06
     unk
    -0.06
     meş
    -0.06
     decad
    -0.06
     danmark
    -0.06
    POSITIVE LOGITS
     Vampire
    0.07
     pela
    0.07
    _references
    0.07
    [tag
    0.06
    .semantic
    0.06
    _RCC
    0.06
    [level
    0.06
    .gnu
    0.06
    [row
    0.06
    .invoke
    0.06
    Act Density 0.000%

    No Known Activations