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

    Neuronpedia

    INDEX
    Explanations

    MV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IL
    1.99
     malah
    1.99
     možda
    1.98
    BAR
    1.95
    是因為
    1.85
     manifestó
    1.84
     Еще
    1.77
     memang
    1.74
     maupun
    1.73
    toluene
    1.71
    POSITIVE LOGITS
    犸
    2.69
     mayhem
    2.58
    gomery
    2.38
     Madness
    2.34
     Mondays
    2.28
     mẽ
    2.28
    та
    2.22
     %>.
    2.22
     importantly
    2.17
    जूदा
    2.11
    Act Density 2.609%

    No Known Activations