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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    って
    -0.07
    ]/
    -0.07
     paved
    -0.06
     dramatic
    -0.06
     velk
    -0.06
    Question
    -0.06
     lớp
    -0.06
     том
    -0.06
    987
    -0.06
     smoke
    -0.06
    POSITIVE LOGITS
    .ListView
    0.07
     Tropical
    0.06
     algun
    0.06
     Panthers
    0.05
     desn
    0.05
     incontr
    0.05
    Targets
    0.05
     Más
    0.05
     Intelligent
    0.05
    Su
    0.05
    Act Density 0.332%

    No Known Activations