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

    Neuronpedia

    INDEX
    Explanations

    Professional Certificate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    、
    0.53
    イ
    0.52
    정
    0.52
    ዖ
    0.48
    정에
    0.47
    Лю
    0.47
    asser
    0.46
    К
    0.46
    тым
    0.46
    주
    0.45
    POSITIVE LOGITS
     Mutant
    0.46
     FU
    0.44
    contentInset
    0.43
    ვილი
    0.43
     রক্ষণ
    0.43
     ATR
    0.42
     Atal
    0.42
    volution
    0.41
    FACT
    0.41
     Therapist
    0.41
    Act Density 0.000%

    No Known Activations