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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and template directives

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

    code delimiters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     souverain
    -0.44
     étoit
    -0.43
     autorité
    -0.41
     itinéraire
    -0.41
     royaume
    -0.40
     Turquie
    -0.40
     nød
    -0.39
     chrétien
    -0.39
     Chinois
    -0.38
     trône
    -0.38
    POSITIVE LOGITS
     {%
    1.46
    {%
    1.44
    }{%
    0.95
    complexContent
    0.88
    <%@
    0.88
    SBATCH
    0.83
    <%=
    0.79
     [%
    0.73
    ="%
    0.71
    Personensuche
    0.71
    Act Density 0.013%

    No Known Activations