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

    Neuronpedia

    INDEX
    Explanations

    XML or data markup syntax

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

    text with quotes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.66
    AnchorStyles
    -0.65
    Personendaten
    -0.61
     ujednoznacz
    -0.59
     phép
    -0.56
     noDo
    -0.56
    BufferException
    -0.55
    Referències
    -0.54
     něko
    -0.54
     artigian
    -0.53
    POSITIVE LOGITS
    alam
    0.44
    aaa
    0.42
    mota
    0.41
    SSS
    0.41
    aa
    0.40
    copyWith
    0.40
    !
    0.39
    RRR
    0.38
     SSS
    0.38
    bbb
    0.38
    Act Density 0.054%

    No Known Activations