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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     negate
    1.06
     worsen
    0.95
    న్లు
    0.94
     reject
    0.94
     elsewhere
    0.93
     местные
    0.93
     persists
    0.91
     excludes
    0.91
    Avoid
    0.91
     mistrust
    0.91
    POSITIVE LOGITS
    ë
    0.76
     wonderful
    0.76
    itura
    0.75
    <start_of_image>
    0.75
    美麗
    0.73
    关于
    0.71
    ța
    0.70
     தமிழ்
    0.70
     తెలుగు
    0.70
     și
    0.68
    Act Density 7.055%

    No Known Activations