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

    Neuronpedia

    INDEX
    Explanations

    escape

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    東西
    -0.08
    prices
    -0.07
    UC
    -0.07
    _planes
    -0.07
    diff
    -0.07
    幅
    -0.07
    _rest
    -0.06
    ¬
    -0.06
    Small
    -0.06
    スーパー
    -0.06
    POSITIVE LOGITS
    绡
    0.07
     Journalism
    0.07
     dejtingsaj
    0.07
     sóc
    0.07
    괸
    0.06
    픙
    0.06
    怎能
    0.06
    ZY
    0.06
    .randint
    0.06
     fend
    0.06
    Act Density 0.025%

    No Known Activations