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

    Neuronpedia

    INDEX
    Explanations

    Continued, value, High

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    éria
    0.40
    iris
    0.38
    classteacher
    0.38
    ஞ்
    0.38
    זור
    0.38
    ئ
    0.38
    ज़ा
    0.37
    ண்ட
    0.36
     Obr
    0.36
    zone
    0.35
    POSITIVE LOGITS
    افيه
    0.40
    専門店
    0.40
     Ent
    0.39
    基础上
    0.38
     nowych
    0.38
    ())),
    0.38
     accessing
    0.38
    োর্টে
    0.38
    entu
    0.38
    뿜
    0.37
    Act Density 0.000%

    No Known Activations