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

    Neuronpedia

    INDEX
    Explanations

    grounds

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    LookAnd
    -0.93
    Datuak
    -0.85
     kasarigan
    -0.82
    MemoryWarning
    -0.79
    parsedMessage
    -0.79
     beſt
    -0.79
    -0.79
    AnchorStyles
    -0.78
    StructEnd
    -0.77
     pleaſure
    -0.74
    POSITIVE LOGITS
     of
    0.56
    s
    0.43
     ord
    0.42
    sor
    0.42
    gica
    0.42
    dach
    0.41
     sor
    0.41
     Ang
    0.40
     write
    0.39
     R
    0.39
    Act Density 1.430%

    No Known Activations