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

    Neuronpedia

    INDEX
    Explanations

    ok

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     classification
    -0.91
    Classification
    -0.90
     Classification
    -0.89
    classification
    -0.85
     ok
    -0.81
     CLASSIFICATION
    -0.78
     okay
    -0.72
     classifications
    -0.70
     OK
    -0.69
    GEBURTSDATUM
    -0.68
    POSITIVE LOGITS
    Geplaatst
    0.67
    IntoConstraints
    0.58
     ujednoznacz
    0.57
     unknownFields
    0.56
    يكب
    0.56
    ible
    0.55
    InitVars
    0.55
    bkz
    0.53
    Vidite
    0.52
    izing
    0.52
    Act Density 1.006%

    No Known Activations