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

    Neuronpedia

    INDEX
    Explanations

    seeking further options or feedback

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     commandes
    0.32
     terpen
    0.32
    𒊒
    0.31
    гий
    0.31
     classifiers
    0.29
     cravings
    0.29
     appartiennent
    0.28
    ژ
    0.28
     calculado
    0.28
    жке
    0.28
    POSITIVE LOGITS
     their
    0.35
     Cement
    0.35
     Their
    0.35
     School
    0.33
     Poor
    0.33
     Myth
    0.33
     Many
    0.32
     তাদের
    0.32
     Very
    0.32
     Considerable
    0.32
    Act Density 0.054%

    No Known Activations