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

    Neuronpedia

    INDEX
    Explanations

    gene documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     (?)
    -0.08
    дел
    -0.07
     intuition
    -0.07
    -0.07
     slope
    -0.07
    yo
    -0.07
    elin
    -0.07
    _FAILED
    -0.07
     damal
    -0.07
     requirements
    -0.07
    POSITIVE LOGITS
     synonyms
    0.15
    aliases
    0.14
     aliases
    0.14
     variations
    0.14
    Variants
    0.14
     variants
    0.14
     вари
    0.13
    Aliases
    0.13
     variantes
    0.13
     Varianten
    0.13
    Act Density 0.036%
    No Known Activations