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

    Neuronpedia

    INDEX
    Explanations

    list formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    uert
    0.38
     крова
    0.32
     two
    0.32
    อร์
    0.31
    еты
    0.31
    coprotein
    0.31
     three
    0.31
    ленный
    0.31
    ractor
    0.30
    uencia
    0.30
    POSITIVE LOGITS
     laissant
    0.44
     WASH
    0.36
    Sprint
    0.35
     HIIT
    0.34
    }$\\
    0.34
     Freestyle
    0.34
    };//
    0.33
    Fry
    0.32
    Batter
    0.32
    Comfort
    0.31
    Act Density 0.000%

    No Known Activations