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

    Neuronpedia

    INDEX
    Explanations

    cotton as a material

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ك
    1.16
     entend
    0.98
     excellently
    0.98
     altre
    0.97
     alem
    0.91
     avem
    0.91
    תו
    0.91
     horizons
    0.91
    ;
    0.90
     semplice
    0.90
    POSITIVE LOGITS
    is
    1.24
     Cotton
    1.24
    em
    1.21
    a
    1.13
    am
    1.08
    و
    1.07
    was
    1.05
    ne
    1.03
    isn
    1.03
    es
    1.02
    Act Density 0.001%

    No Known Activations