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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    ↵
    -0.25
     aujourd
    -0.24
    F
    -0.23
     saying
    -0.23
    ഔ
    -0.22
    </code>
    -0.22
    ­
    -0.22
    line
    -0.22
     says
    -0.21
     enig
    -0.21
    POSITIVE LOGITS
    wiliwch
    0.84
    ſehen
    0.84
     ſelb
    0.83
    <unused43>
    0.82
    <unused41>
    0.82
    <unused55>
    0.82
    ſſung
    0.82
    <unused21>
    0.82
    <unused15>
    0.82
    <unused8>
    0.82
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.