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

    Neuronpedia

    INDEX
    Explanations

    Academic texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gracious
    -0.07
    prove
    -0.07
    ☞
    -0.07
    엶
    -0.07
    ㎡
    -0.07
    杄
    -0.07
    雎
    -0.07
     NOI
    -0.07
    ptide
    -0.07
    😂
    -0.06
    POSITIVE LOGITS
     sacrific
    0.07
    游戏
    0.07
    -account
    0.06
    .part
    0.06
     ranges
    0.06
    התחיל
    0.06
    _stream
    0.06
     formul
    0.06
     ECS
    0.06
     extends
    0.06
    Act Density 0.017%

    No Known Activations