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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    laws
    -0.69
    rine
    -0.68
    bane
    -0.66
    eve
    -0.64
     Depths
    -0.64
     Orbital
    -0.64
     Nebula
    -0.63
     istg
    -0.62
    gal
    -0.61
    Radio
    -0.61
    POSITIVE LOGITS
     contrace
    0.72
    ãĤ§
    0.70
     TI
    0.70
    vier
    0.68
     exting
    0.68
     paternity
    0.64
     trout
    0.64
    reci
    0.62
     adul
    0.62
    Īè
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.