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

    Neuronpedia

    INDEX
    Explanations

    computer code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Interest
    -0.06
    Fant
    -0.06
    ункт
    -0.06
     Integr
    -0.06
     Def
    -0.06
    _site
    -0.06
     airports
    -0.06
    Listing
    -0.06
    (using
    -0.06
     iff
    -0.06
    POSITIVE LOGITS
     Shard
    0.07
     biased
    0.07
    .userService
    0.07
    入れ
    0.06
    登
    0.06
    nám
    0.06
     signage
    0.06
     melting
    0.06
    _FAILED
    0.06
    ventus
    0.06
    Act Density 0.013%

    No Known Activations