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

    Neuronpedia

    INDEX
    Explanations

    code explanation and generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     endast
    1.23
     שלך
    1.15
    ร
    1.11
     atténuées
    1.09
    țională
    1.08
     केवल
    1.06
    বিল
    1.05
     Dernière
    1.05
    నె
    1.05
     лише
    1.05
    POSITIVE LOGITS
     volcano
    1.02
    AddTo
    0.98
     Mata
    0.95
    폰
    0.92
    ುದು
    0.90
    ский
    0.90
     change
    0.89
    change
    0.88
    ేష్
    0.88
    inf
    0.88
    Act Density 0.000%

    No Known Activations