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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     mathemat
    -0.66
     nonsensical
    -0.64
    paio
    -0.64
    ħĭ
    -0.60
    odynamic
    -0.59
    soDeliveryDate
    -0.59
    stad
    -0.58
     disciplines
    -0.57
    bleacher
    -0.57
    actic
    -0.57
    POSITIVE LOGITS
     msec
    0.71
    eating
    0.69
    idable
    0.68
     Leban
    0.68
    come
    0.65
     Sof
    0.65
    Hug
    0.64
     Lum
    0.62
     Zig
    0.62
     Buch
    0.61
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.