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

    Neuronpedia

    INDEX
    Explanations

    instances of significant numerical values or statistics

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

    years and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -0.71
     utafitiHapana
    -0.68
    ﹧
    -0.65
    ஬
    -0.65
    <unused73>
    -0.65
    <unused41>
    -0.64
    <unused23>
    -0.64
    <unused32>
    -0.64
    <unused3>
    -0.64
    <unused16>
    -0.64
    POSITIVE LOGITS
    FunctionFlags
    0.35
    </h2>
    0.29
     Egipto
    0.28
     bedo
    0.28
    Pres
    0.25
    </h3>
    0.24
     kemarin
    0.24
    hasMoreElements
    0.23
    createCanvas
    0.23
     Wald
    0.23
    Act Density 0.050%

    No Known Activations