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

    Neuronpedia

    INDEX
    Explanations

    say '] followed by punctuation'

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pun
    -0.07
    PRECATED
    -0.07
     Kur
    -0.07
     pur
    -0.07
    _SAN
    -0.07
    führen
    -0.06
    >About
    -0.06
     Prague
    -0.06
     Quentin
    -0.06
     ust
    -0.06
    POSITIVE LOGITS
     LO
    0.07
    海外
    0.07
     William
    0.07
    Actions
    0.07
    Tracking
    0.06
     ACTION
    0.06
    	Query
    0.06
    velope
    0.06
    包装
    0.06
    ัด
    0.06
    Act Density 0.019%

    No Known Activations