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

    Neuronpedia

    INDEX
    Explanations

    introduces explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rumoured
    0.33
     tor
    0.32
     promin
    0.30
    եց
    0.30
     foam
    0.30
    部に
    0.30
    _",
    0.30
     trem
    0.29
     ஆகிய
    0.29
     atop
    0.29
    POSITIVE LOGITS
    也就是说
    0.68
     অর্থাৎ
    0.59
    所以在
    0.53
    অর্থাৎ
    0.53
     所以
    0.52
     это
    0.51
     Therefore
    0.50
    Therefore
    0.48
     அதாவது
    0.48
     म्हणजेच
    0.48
    Act Density 0.203%

    No Known Activations