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

    Neuronpedia

    INDEX
    Explanations

    classification

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Над
    -0.07
    �
    -0.07
     holes
    -0.07
    uminum
    -0.06
     ends
    -0.06
    œur
    -0.06
    ircle
    -0.06
     hole
    -0.06
     proposes
    -0.06
     حضور
    -0.06
    POSITIVE LOGITS
     classified
    0.11
     classify
    0.11
     classification
    0.10
     Classified
    0.09
    classify
    0.08
     classifier
    0.08
    classified
    0.08
    Classification
    0.08
    Classifier
    0.08
     status
    0.07
    Act Density 0.017%

    No Known Activations