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

    Neuronpedia

    INDEX
    Explanations

    LaTeX formatting and mathematical symbols

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

    Square brackets containing a short string

    np_acts-logits-general · gemini-2.0-flash

    mathematical notation and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ISupport
    -1.01
    PARATUS
    -0.64
     Exactos
    -0.59
    transQ
    -0.57
    FailureListener
    -0.56
    ibol
    -0.56
     समीक्षाएं
    -0.56
     mxArray
    -0.53
    CompleteListener
    -0.53
    Tazama
    -0.52
    POSITIVE LOGITS
    thâu
    0.54
    Cyfeiriadau
    0.46
     handelt
    0.46
     \
    0.45
    CAPTION
    0.45
    fycat
    0.44
     gynnwys
    0.43
    \\\
    0.42
    Batis
    0.41
    Cyfarwyddwr
    0.41
    Act Density 0.060%

    No Known Activations