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

    Neuronpedia

    INDEX
    Explanations

    SQL alias

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adidas
    -0.07
     haus
    -0.07
     suporta
    -0.07
     drunk
    -0.07
    完整
    -0.07
     sentido
    -0.07
     comprov
    -0.07
     enormous
    -0.07
     Random
    -0.07
     ಲಕ್ಷ
    -0.07
    POSITIVE LOGITS
     aliases
    0.16
    .rename
    0.15
     rename
    0.15
     renamed
    0.15
     alias
    0.15
    (rename
    0.14
    aliases
    0.14
    alias
    0.14
    Aliases
    0.14
    _alias
    0.13
    Act Density 0.006%

    No Known Activations