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

    Neuronpedia

    INDEX
    Explanations

    conditional intent "you want"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     бонус
    0.44
     dute
    0.38
    ἀ
    0.38
     бонусы
    0.36
     Achilles
    0.36
     Hoyt
    0.36
    пь
    0.36
    émi
    0.36
     কচ
    0.35
    امي
    0.35
    POSITIVE LOGITS
    yloxy
    0.44
     prominently
    0.44
     sab
    0.39
    erar
    0.38
     malattia
    0.37
    ListOf
    0.36
     corrispond
    0.36
     कभी
    0.36
     mots
    0.36
     bernama
    0.36
    Act Density 0.001%

    No Known Activations