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

    Neuronpedia

    INDEX
    Explanations

    dash

    np_max-act · gemini-2.0-flash

    dates and year numbers within historical or academic texts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @tatsatx
    New Auto-Interp
    Negative Logits
     Marilyn
    -0.09
    াকা
    -0.08
    -mar
    -0.08
     farmer
    -0.08
     сертифик
    -0.08
    -fired
    -0.08
     gente
    -0.07
    secure
    -0.07
    verde
    -0.07
     eigener
    -0.07
    POSITIVE LOGITS
     ext
    0.07
    月至
    0.07
     الو
    0.07
    จน
    0.07
     rè
    0.07
     LTE
    0.07
     Ae
    0.07
    .iter
    0.07
    �
    0.07
     Incorpor
    0.07
    Act Density 0.025%

    No Known Activations