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

    Neuronpedia

    INDEX
    Explanations

    on its own

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    пе
    0.96
    ize
    0.94
     tener
    0.91
     seri
    0.90
    ../../
    0.89
     dollars
    0.88
     lalu
    0.88
     sami
    0.87
    0.87
     rend
    0.87
    POSITIVE LOGITS
    comboBox
    1.34
    鶘
    1.19
    heartedly
    1.19
    swick
    1.16
    addKill
    1.15
    ྐ
    1.11
    жала
    1.11
     обладает
    1.11
    starch
    1.10
    いただけます
    1.08
    Act Density 0.070%

    No Known Activations