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

    Neuronpedia

    INDEX
    Explanations

    placeholders and structural elements in programming code

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

    Log messages and errors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    -0.31
    though
    -0.30
    —
    -0.29
    rceil
    -0.29
    中
    -0.28
     Though
    -0.27
     jednak
    -0.27
    　
    -0.27
    .
    -0.26
    esti
    -0.26
    POSITIVE LOGITS
     AssemblyTitle
    0.87
    <unused16>
    0.83
     betweenstory
    0.83
    <unused51>
    0.83
    <unused42>
    0.83
    <unused14>
    0.83
    <unused43>
    0.83
    <unused52>
    0.83
    <unused80>
    0.83
    <unused3>
    0.82
    Act Density 0.040%

    No Known Activations