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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    bootstrapcdn
    -0.77
    saraba
    -0.77
     uska
    -0.58
    tagext
    -0.54
    stdbool
    -0.48
     PyTuple
    -0.48
    claimer
    -0.48
     himo
    -0.47
    demort
    -0.47
    aktery
    -0.47
    POSITIVE LOGITS
     pleaſure
    0.57
     Confidentiality
    0.57
     JURIS
    0.54
     ſch
    0.53
     AssemblyTitle
    0.51
    OGND
    0.50
     geïsole
    0.50
     Burnet
    0.49
    ürtel
    0.49
     Metadata
    0.49
    Act Density 0.016%

    No Known Activations