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

    Neuronpedia

    INDEX
    Explanations

    words ending in ary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ረሻ
    0.40
    attuale
    0.40
    吸收
    0.39
    ROIT
    0.39
    sonar
    0.38
    issau
    0.38
    ikte
    0.38
    ジタル
    0.38
    চ্ছিল
    0.38
     ULT
    0.36
    POSITIVE LOGITS
    mann
    0.38
     Funny
    0.38
    λευ
    0.38
    man
    0.38
    Different
    0.38
    ingly
    0.37
    more
    0.37
    llium
    0.37
     parvenir
    0.37
    lus
    0.36
    Act Density 0.006%

    No Known Activations