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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Gibraltar
    -0.75
     autos
    -0.73
    UES
    -0.68
    Ô
    -0.67
    eu
    -0.67
     Ruk
    -0.66
    Unix
    -0.65
    avan
    -0.64
    eve
    -0.64
    abeth
    -0.63
    POSITIVE LOGITS
    Bottom
    0.73
    claw
    0.71
    kinson
    0.69
     Ranking
    0.68
    Bound
    0.67
     limb
    0.65
    Connector
    0.64
    alloc
    0.63
    rotein
    0.63
    ionics
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.