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

    Neuronpedia

    INDEX
    Explanations

    Stop words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Configuration
    -0.08
     varieties
    -0.07
     toujours
    -0.07
    <Date
    -0.07
    纬
    -0.07
    _migration
    -0.07
    𝐤
    -0.07
     قيمة
    -0.06
     declaring
    -0.06
    _ru
    -0.06
    POSITIVE LOGITS
     PAS
    0.07
    ees
    0.07
    -workers
    0.07
    users
    0.07
    BOOK
    0.07
     baby
    0.07
     �
    0.06
     pea
    0.06
    for
    0.06
    딕
    0.06
    Act Density 0.079%

    No Known Activations