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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    physical
    -0.75
    ãĥ³ãĤ¸
    -0.71
    arb
    -0.70
    ãĥª
    -0.69
    ãĤ¤ãĥĪ
    -0.69
     Kahn
    -0.68
    sed
    -0.65
    RPG
    -0.65
    ãĥ´ãĤ¡
    -0.64
     Agg
    -0.64
    POSITIVE LOGITS
    letters
    0.74
     lapt
    0.74
     ado
    0.68
     millenn
    0.68
    reader
    0.67
     unlaw
    0.66
     inconsist
    0.66
     blat
    0.66
     GOODMAN
    0.64
     specificity
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.