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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    分类
    -0.08
    ’on
    -0.08
     classify
    -0.08
     igra
    -0.08
     rely
    -0.07
     assessment
    -0.07
     classification
    -0.07
     -*-↵
    -0.07
    _flutter
    -0.07
    Classification
    -0.07
    POSITIVE LOGITS
     Autos
    0.10
     Consum
    0.08
    Marie
    0.08
     affin
    0.08
     Oreo
    0.08
     Submitted
    0.08
     roasted
    0.08
     massac
    0.08
     descended
    0.08
     Buen
    0.08
    Act Density 0.007%

    No Known Activations