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

    Neuronpedia

    INDEX
    Explanations

    completeness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HashSet
    -0.07
    plements
    -0.06
     Gotham
    -0.06
    生成
    -0.06
     Leg
    -0.06
     tents
    -0.06
     Card
    -0.06
     답
    -0.06
     Reward
    -0.06
     Couldn
    -0.06
    POSITIVE LOGITS
    AllowAnonymous
    0.07
    ...,
    0.07
     escal
    0.06
    Fcn
    0.06
     renters
    0.06
    備
    0.06
    Terminate
    0.06
    .Promise
    0.06
     ま
    0.06
    ัดส
    0.06
    Act Density 0.039%

    No Known Activations