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

    Neuronpedia

    INDEX
    Explanations

    coding syntax and programming structure elements

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

    graphics code elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused28>
    -0.96
    <unused8>
    -0.96
    <unused43>
    -0.96
    <unused51>
    -0.96
    <unused14>
    -0.96
    <unused3>
    -0.96
    <unused17>
    -0.96
    <unused32>
    -0.96
    <pad>
    -0.96
    [@BOS@]
    -0.96
    POSITIVE LOGITS
    🎨
    0.42
     artistic
    0.39
     art
    0.35
     graphics
    0.35
     visual
    0.35
    fillStyle
    0.33
    She
    0.33
     artístico
    0.32
     Art
    0.31
     color
    0.31
    Act Density 0.014%

    No Known Activations