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

    Neuronpedia

    INDEX
    Explanations

    legal identifiers and references in documents

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

    legal citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sizeCache
    -0.98
     queſta
    -0.98
     surla
    -0.92
     ſind
    -0.85
    OGND
    -0.84
    iſen
    -0.81
    fjspx
    -0.80
    ſchaft
    -0.80
     $_(
    -0.79
    <unused8>
    -0.79
    POSITIVE LOGITS
    1
    0.38
    ).
    0.33
     says
    0.32
    2
    0.31
    。
    0.31
     Wege
    0.30
    .
    0.30
    <eos>
    0.29
    //
    0.29
     Zeits
    0.29
    Act Density 0.156%

    No Known Activations