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

    Neuronpedia

    INDEX
    Explanations

    fun and tricky tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    υσ
    0.47
    曷
    0.45
    Zs
    0.42
     আসতে
    0.40
     সূ
    0.39
    ्डा
    0.38
    抨
    0.38
     Hoffnung
    0.38
    銜
    0.37
    alassem
    0.36
    POSITIVE LOGITS
    ervice
    0.42
     varied
    0.42
    ായിരുന്നു
    0.40
     surprises
    0.39
     betting
    0.38
     appetizing
    0.37
    Serving
    0.36
     varies
    0.36
    有好
    0.36
    魅力
    0.35
    Act Density 0.000%

    No Known Activations