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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    <h2>
    0.49
    hört
    0.40
    ación
    0.40
    ocam
    0.40
    onar
    0.40
    rica
    0.40
    ichtung
    0.40
    準備
    0.40
    <0x81>
    0.39
    星座
    0.39
    POSITIVE LOGITS
     bunnies
    0.55
     eksper
    0.52
     acetic
    0.52
     buty
    0.52
     eruptions
    0.51
     संख्या
    0.51
     endings
    0.51
     antara
    0.50
     esters
    0.49
     injuries
    0.49
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.