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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ido
    -0.80
    etts
    -0.78
    actionDate
    -0.77
    nas
    -0.73
    ins
    -0.72
    indu
    -0.72
    ļéĨĴ
    -0.71
    syn
    -0.70
    iles
    -0.70
    ival
    -0.70
    POSITIVE LOGITS
     Gaia
    0.76
    ufact
    0.73
     flakes
    0.71
     Crusher
    0.69
     lightly
    0.64
     wip
    0.63
     Robotics
    0.63
     flora
    0.63
     Nept
    0.62
     caut
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.