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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     stumbled
    0.79
     nouns
    0.78
     absorbs
    0.75
     collected
    0.72
    cribing
    0.71
     derived
    0.70
     Sociology
    0.70
     spiders
    0.70
     spider
    0.69
     Passion
    0.68
    POSITIVE LOGITS
    то
    0.79
    ävä
    0.78
    י
    0.77
    dann
    0.75
    м
    0.75
    em
    0.75
    у
    0.75
    개가
    0.73
    unico
    0.73
    ne
    0.71
    Act Density 0.001%

    No Known Activations