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

    Neuronpedia

    INDEX
    Explanations

    available, incredible, declarative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ت
    2.52
    ிருந்தால்
    2.44
    ″
    2.40
    ν
    2.21
    𝐔
    2.19
    ⃣
    2.18
    䣫
    2.11
    䣷
    2.08
    ிருந்தது
    2.06
    HING
    2.05
    POSITIVE LOGITS
    ar
    2.22
    ined
    2.02
    ောင့်
    1.74
    etics
    1.74
    ining
    1.74
    ol
    1.73
    uing
    1.71
    htub
    1.71
    ib
    1.64
     Besonders
    1.63
    Act Density 0.381%

    No Known Activations