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

    Neuronpedia

    INDEX
    Explanations

    code structure and syntax elements in programming languages

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

    code snippets or HTML

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <!--[
    -0.33
    AdapterView
    -0.29
     either
    -0.26
    eqn
    -0.26
    ZIONE
    -0.25
     Re
    -0.25
     légale
    -0.25
     stran
    -0.25
     eingel
    -0.25
     gere
    -0.25
    POSITIVE LOGITS
     initComponents
    0.77
    [@BOS@]
    0.77
    <unused3>
    0.76
    <unused8>
    0.76
    <unused51>
    0.76
    <unused74>
    0.76
    <unused47>
    0.76
    <unused43>
    0.76
    <unused28>
    0.76
    <unused41>
    0.76
    Act Density 0.031%

    No Known Activations