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

    Neuronpedia

    INDEX
    Explanations

    shapes and structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _disconnect
    -0.09
     URLs
    -0.08
    .disconnect
    -0.08
     Babel
    -0.08
     phrases
    -0.08
     frases
    -0.08
    .')↵↵
    -0.08
    _urls
    -0.08
     Grandma
    -0.08
    Disconnect
    -0.08
    POSITIVE LOGITS
     thickness
    0.10
    adius
    0.09
     hull
    0.09
     cylinder
    0.09
     width
    0.09
     tubular
    0.09
     radius
    0.09
     tube
    0.09
     tire
    0.09
    Thickness
    0.08
    Act Density 0.038%

    No Known Activations