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

    Neuronpedia

    INDEX
    Explanations

    technical and mathematical expressions related to functions and examples

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

    example in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :+:
    -0.30
     cerrados
    -0.27
    ="@+
    -0.25
     انداز
    -0.25
     खु
    -0.24
     tanul
    -0.24
     coû
    -0.23
    niejsze
    -0.23
    RTDA
    -0.23
     desem
    -0.22
    POSITIVE LOGITS
     الحره
    0.74
     الرياضيه
    0.65
    قایناقلار
    0.59
     utafitiHapana
    0.58
    oa̍t
    0.56
     OMITBAD
    0.55
     كومونز
    0.55
    msgTypes
    0.54
    ImageContext
    0.54
    0.53
    Act Density 0.101%

    No Known Activations