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

    Neuronpedia

    INDEX
    Explanations

    homicide and email contact

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    лили
    0.51
    лил
    0.50
     Ingers
    0.49
    អារ
    0.48
     типа
    0.48
     típus
    0.47
    स
    0.46
     Bhagava
    0.46
    䍩
    0.45
    脛
    0.44
    POSITIVE LOGITS
     donner
    0.49
     better
    0.46
    ୂ
    0.44
    automne
    0.42
    wo
    0.42
     wo
    0.42
     documentary
    0.42
    toc
    0.42
     considered
    0.41
     declared
    0.41
    Act Density 0.001%

    No Known Activations