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

    Neuronpedia

    INDEX
    Explanations

    code-like structures or object definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    processing code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aarrggbb
    -0.47
    :],
    -0.40
    riwal
    -0.38
    Ɓ
    -0.36
    :][
    -0.35
     بلکه
    -0.34
    jimo
    -0.34
    kert
    -0.34
     {};
    -0.34
     terp
    -0.33
    POSITIVE LOGITS
     protoimpl
    0.56
     informée
    0.55
     يتيمه
    0.55
     kasarigan
    0.55
     initWithFrame
    0.52
    GraphicsUnit
    0.51
    MessageOf
    0.50
    ($__
    0.50
     مرئيه
    0.48
    Rüyada
    0.48
    Act Density 0.115%

    No Known Activations