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

    Neuronpedia

    INDEX
    Explanations

    dent and lent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Crystallogr
    0.43
     何
    0.38
    팎
    0.37
     अबा
    0.36
    絘
    0.36
    ྱི་
    0.35
    ອອກ
    0.35
     क्रिप्ट
    0.35
     ไง
    0.35
    тивным
    0.35
    POSITIVE LOGITS
     dent
    0.52
     dents
    0.48
    జర్
    0.47
     lenta
    0.40
     жер
    0.40
     leistungs
    0.39
    볕
    0.39
    zel
    0.39
     hình
    0.39
     jar
    0.39
    Act Density 0.007%

    No Known Activations