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

    Neuronpedia

    INDEX
    Explanations

    code snippets, function calls

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     énerg
    0.49
     enzym
    0.48
     éclair
    0.48
     ém
    0.48
     escul
    0.48
     affaires
    0.48
     urin
    0.48
     harmonies
    0.48
     reminis
    0.47
     hadiah
    0.47
    POSITIVE LOGITS
    0.65
    //
    0.64
    is
    0.63
    0.53
    _
    0.52
    A
    0.50
    0.49
    0.47
    (
    0.47
    {
    0.47
    Act Density 0.114%

    No Known Activations