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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     coded
    -0.08
     axiom
    -0.07
    荒
    -0.07
     Lincoln
    -0.07
    立
    -0.07
     hafif
    -0.07
     zi
    -0.06
    IALIZ
    -0.06
     konusu
    -0.06
     divisions
    -0.06
    POSITIVE LOGITS
     stun
    0.06
     Bliss
    0.06
    -assets
    0.06
    .profile
    0.06
    션
    0.06
    loat
    0.06
    ListView
    0.06
     coupon
    0.06
     microtime
    0.06
     resultList
    0.06
    Act Density 0.001%

    No Known Activations