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

    Neuronpedia

    INDEX
    Explanations

    closing tags and conditional statements in programming or templating languages

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

    closing conditional blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '},
    -0.81
    "){
    -0.81
    "},
    -0.79
     lyre
    -0.78
     Shakspeare
    -0.74
     myſelf
    -0.72
     pleaſure
    -0.70
    {
    -0.70
    '),
    -0.69
    "),
    -0.68
    POSITIVE LOGITS
     endif
    1.03
    endif
    0.92
    .
    0.64
    queles
    0.54
    ENDIF
    0.52
     endwhile
    0.51
     endforeach
    0.47
    endregion
    0.46
    PerformLayout
    0.46
     endblock
    0.46
    Act Density 0.008%

    No Known Activations