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

    Neuronpedia

    INDEX
    Explanations

    However, certain topics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     深
    0.45
     जाऊ
    0.39
    ſelf
    0.38
    深く
    0.38
    深
    0.37
    ancies
    0.37
     Bronco
    0.37
     ráp
    0.37
    素敵
    0.37
    ちは
    0.36
    POSITIVE LOGITS
    Routine
    0.43
    ೃಷ್ಟ
    0.41
     atm
    0.41
    Atm
    0.39
     algumas
    0.39
    মস
    0.38
    ATM
    0.38
     algunas
    0.38
     وړاند
    0.37
     Atm
    0.37
    Act Density 0.000%

    No Known Activations