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

    Neuronpedia

    INDEX
    Explanations

    performance metrics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ervices
    0.43
    ervice
    0.42
     ট্রান্স
    0.41
    anton
    0.41
     principio
    0.40
    ansive
    0.40
     Hafen
    0.40
     harbour
    0.40
    abbati
    0.39
    onnements
    0.39
    POSITIVE LOGITS
    ویر
    0.48
    Mesh
    0.44
     prematurely
    0.43
    Binary
    0.41
     clarify
    0.40
    Bond
    0.40
    Explicit
    0.40
    दो
    0.40
     qīng
    0.40
    Py
    0.39
    Act Density 0.125%

    No Known Activations