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

    Neuronpedia

    INDEX
    Explanations

    comments or markup related to computer hardware specifications

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

    pipeline parameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.53
     autoridad
    -0.48
     magique
    -0.47
     franquicia
    -0.47
     normalidad
    -0.46
     courbe
    -0.44
    PhysRevD
    -0.44
    rungsseite
    -0.43
     burbuja
    -0.43
     réparation
    -0.43
    POSITIVE LOGITS
    <!--
    0.92
     <!--
    0.75
    __(/*!
    0.63
     Faux
    0.56
    <!--[
    0.56
    <!--<
    0.54
     Jana
    0.53
    <%=
    0.52
    <!--
    0.52
    ><!--
    0.51
    Act Density 0.012%

    No Known Activations