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

    Neuronpedia

    INDEX
    Explanations

    phrases related to legal interpretations and arguments

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

    explaining or describing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.69
    Hentet
    -0.63
     zwiſchen
    -0.63
    aarrggbb
    -0.62
     defaultstate
    -0.62
    Datuak
    -0.62
    tender
    -0.61
     ویکی‌پدیای
    -0.61
     ostavi
    -0.59
    istoitu
    -0.59
    POSITIVE LOGITS
     espíritu
    0.34
    ngdoc
    0.31
    contentLoaded
    0.29
    IntoConstraints
    0.28
     motocicleta
    0.25
     initComponents
    0.25
     esclavos
    0.24
     интере
    0.24
     -->
    0.24
     →
    0.23
    Act Density 0.851%

    No Known Activations