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

    Neuronpedia

    INDEX
    Explanations

    don't want to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unable
    0.32
     in
    0.30
    Пра
    0.30
     within
    0.28
     Assets
    0.28
    In
    0.28
     peric
    0.27
     provides
    0.27
    polygon
    0.26
     constraints
    0.26
    POSITIVE LOGITS
     necessarily
    0.32
     bloody
    0.31
     hafta
    0.31
     fucking
    0.31
     bother
    0.30
     know
    0.30
     siquiera
    0.29
    ckie
    0.29
    know
    0.29
     شفنا
    0.29
    Act Density 0.011%

    No Known Activations