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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    sourced
    0.82
     sharks
    0.78
     newspap
    0.75
    তাহাদের
    0.75
    aughters
    0.73
     Sharks
    0.72
     veneer
    0.72
    ត្រូ
    0.72
     thisobject
    0.71
    ptious
    0.71
    POSITIVE LOGITS
    M
    0.94
    AND
    0.79
     дво
    0.73
    H
    0.73
    ING
    0.72
     било
    0.71
     била
    0.68
     M
    0.67
    u
    0.63
    би
    0.63
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.