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

    Neuronpedia

    INDEX
    Explanations

    csv

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _EQ
    -0.08
    -gap
    -0.07
     retired
    -0.07
    ګ
    -0.07
     videot
    -0.07
    ária
    -0.07
    スーパー
    -0.07
    憧憬
    -0.07
    .ep
    -0.07
    ւ
    -0.07
    POSITIVE LOGITS
    '),
    0.07
    "]:
    0.06
    加盟商
    0.06
    却发现
    0.06
     '',
    0.06
     castle
    0.06
    predictions
    0.06
    してくれる
    0.06
     alerts
    0.06
    ")↵
    0.06
    Act Density 0.003%

    No Known Activations