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

    Neuronpedia

    INDEX
    Explanations

    legal/financial failures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Complaint
    -0.07
    Ptr
    -0.07
    .toString
    -0.06
     async
    -0.06
     constitu
    -0.06
    _requests
    -0.06
     Ön
    -0.06
     pitfalls
    -0.06
    좌
    -0.06
    blocking
    -0.06
    POSITIVE LOGITS
    renom
    0.08
    bac
    0.07
    이션
    0.06
    _CATEGORY
    0.06
     stabilize
    0.06
     stabilized
    0.06
    เสนอ
    0.06
     ков
    0.06
     adventurer
    0.06
    ramework
    0.06
    Act Density 0.022%

    No Known Activations