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

    Neuronpedia

    INDEX
    Explanations

    elements related to personal experience and emotional expression

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

    referencing previous statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Bourgoin
    -0.43
     rispond
    -0.41
     yapıl
    -0.40
    aarrggbb
    -0.38
     limone
    -0.37
    Nosotros
    -0.37
     Glas
    -0.36
     Pitman
    -0.36
     Moon
    -0.36
     Tone
    -0.36
    POSITIVE LOGITS
     autorytatywna
    0.56
    tanleria
    0.54
     المعيارى
    0.51
    AndEndTag
    0.44
    \{\\
    0.43
    />";
    0.40
    addCriterion
    0.40
    gelopen
    0.39
    withIdentifier
    0.39
     HasFactory
    0.39
    Act Density 0.041%

    No Known Activations