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

    Neuronpedia

    INDEX
    Explanations

    decorating, adorableness

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     decorate
    -0.85
    ">//
    -0.76
    itudinal
    -0.75
    orship
    -0.73
    tagHelperRunner
    -0.73
    🏻
    -0.69
    Composable
    -0.67
    termilk
    -0.66
     betweenstory
    -0.66
    tons
    -0.64
    POSITIVE LOGITS
     Enter
    0.52
     juges
    0.50
     Lern
    0.48
    innis
    0.47
     memen
    0.47
     addresses
    0.47
    </i>
    0.45
     soldati
    0.44
     from
    0.43
     addressed
    0.43
    Act Density 0.058%

    No Known Activations