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

    Neuronpedia

    INDEX
    Explanations

    chameleon, seahorse, holding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drug
    0.46
     places
    0.42
     Iowa
    0.42
    drug
    0.42
    ドン
    0.41
     magie
    0.41
     tentacles
    0.40
     possibilities
    0.40
    있다
    0.40
    더
    0.40
    POSITIVE LOGITS
     və
    0.50
     Kasım
    0.46
     şi
    0.42
     selaku
    0.42
    展现
    0.42
     și
    0.40
    ərə
    0.40
    ませんが
    0.39
     మరియు
    0.39
    akur
    0.38
    Act Density 0.004%

    No Known Activations