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

    Neuronpedia

    INDEX
    Explanations

    ruby each do iteration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     iterate
    0.45
     lur
    0.41
     iterates
    0.39
     )),
    0.39
     séqu
    0.38
     °,
    0.38
     отриму
    0.38
     бывает
    0.37
    能在
    0.37
     operates
    0.37
    POSITIVE LOGITS
    {|
    0.53
    }|
    0.48
    }}{|
    0.45
     do
    0.45
    ,|\
    0.45
    ffe
    0.43
    }{|
    0.41
     "|
    0.41
    eng
    0.40
    │
    0.40
    Act Density 0.000%

    No Known Activations