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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and equations

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

    LaTeX equations/mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    alignment related words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    diac
    -0.60
    irl
    -0.51
    complexType
    -0.49
    formik
    -0.49
     girl
    -0.48
     tito
    -0.48
     diversify
    -0.47
     Bernie
    -0.47
     Bolivar
    -0.47
    WithMany
    -0.47
    POSITIVE LOGITS
    expandindo
    0.78
     rospy
    0.71
     }}"></
    0.70
     CreateTagHelper
    0.67
     />';
    0.65
    ("]");
    0.63
    )';
    0.62
     مشين
    0.62
     ویکی‌پدیای
    0.61
    ."</
    0.61
    Act Density 0.087%

    No Known Activations