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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    unders
    -0.88
     mathemat
    -0.81
    "]=>
    -0.81
    ãĥ¯ãĥ³
    -0.79
    llor
    -0.74
    è¦ļéĨĴ
    -0.71
    rolet
    -0.71
    esm
    -0.71
    anni
    -0.69
     ministers
    -0.68
    POSITIVE LOGITS
    scene
    0.72
     stere
    0.70
    rop
    0.68
    teenth
    0.67
     locker
    0.67
     Peninsula
    0.64
     anonymous
    0.63
     pes
    0.63
    verse
    0.62
     voy
    0.62
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.