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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Ø
    -0.74
     cycle
    -0.73
     triangle
    -0.70
     ãĤ
    -0.69
     flowed
    -0.68
    âĢ²
    -0.66
     Gard
    -0.63
     Clare
    -0.62
     occurred
    -0.62
     Carlo
    -0.62
    POSITIVE LOGITS
    oby
    0.80
    addons
    0.77
    oths
    0.77
    avascript
    0.76
    ikuman
    0.72
    task
    0.70
    ypes
    0.70
    atom
    0.69
    rozen
    0.69
    utm
    0.68
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.