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

    Neuronpedia

    INDEX
    Explanations

    XML or HTML-like syntax elements and their attributes

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

    markup structure and code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.61
     colecciones
    -0.60
     Biôgrafia
    -0.58
    AndEndTag
    -0.55
    ConstraintMaker
    -0.53
    GraphicsUnit
    -0.52
    igslist
    -0.51
    jsxFileName
    -0.50
    anasia
    -0.50
     Sünde
    -0.49
    POSITIVE LOGITS
     Adam
    0.42
    Adam
    0.40
     closed
    0.40
     extra
    0.39
    ρίες
    0.38
     gamb
    0.38
    tein
    0.37
    Extra
    0.36
    TypedDataSet
    0.36
     ab
    0.36
    Act Density 0.002%

    No Known Activations