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

    Neuronpedia

    INDEX
    Explanations

    Cape or winter locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     winter
    -0.91
    <bos>
    -0.84
     Cape
    -0.75
     crdi
    -0.75
     winters
    -0.74
     ModelExpression
    -0.72
     purpoſe
    -0.72
     myſelf
    -0.71
     '\\;'
    -0.69
    Cape
    -0.68
    POSITIVE LOGITS
    place
    0.70
    time
    0.65
    fied
    0.56
    matic
    0.54
    ging
    0.53
    back
    0.50
    ged
    0.50
     pinulongan
    0.50
    glä
    0.50
    wise
    0.50
    Act Density 0.118%

    No Known Activations