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

    Neuronpedia

    INDEX
    Explanations

    structured data references and formats

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

    Category

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     AssemblyVersion
    -0.71
    +#+
    -0.59
    RenderAtEndOf
    -0.57
    ſelf
    -0.57
    ſelves
    -0.54
    LookAnd
    -0.54
    expandindo
    -0.53
    sidemargin
    -0.53
     الرياضيه
    -0.52
     ſche
    -0.52
    POSITIVE LOGITS
     tit
    0.46
     tem
    0.44
     пора
    0.42
    שמי
    0.41
     об
    0.41
     Spann
    0.39
    новниш
    0.39
    الحياه
    0.38
     typically
    0.37
     Tit
    0.37
    Act Density 0.050%

    No Known Activations