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

    Neuronpedia

    INDEX
    Explanations

    generate responses or creative roles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kových
    0.44
     Systems
    0.41
    পর্ব
    0.41
    気温
    0.41
     Sistemas
    0.41
     Tick
    0.40
     Gazette
    0.40
     Corps
    0.40
    成员
    0.40
    ونکو
    0.40
    POSITIVE LOGITS
    </
    0.40
     ､
    0.40
     _;
    0.39
     о
    0.38
    鳌
    0.38
     ш
    0.38
    明らかに
    0.37
     assimilate
    0.37
     ，
    0.36
     __('
    0.36
    Act Density 0.020%

    No Known Activations