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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    Full
    0.70
     puedes
    0.68
    Invitrogen
    0.67
     cocoon
    0.66
     mage
    0.66
     unstoppable
    0.65
    quakes
    0.64
     ayudarte
    0.64
     masterpiece
    0.63
     கொள்ளலாம்
    0.63
    POSITIVE LOGITS
    產
    0.73
    ల్
    0.70
    $-\
    0.69
    دت
    0.65
    ovaž
    0.65
    го
    0.62
    essa
    0.62
     inom
    0.61
    ტერ
    0.61
    ductory
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.