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

    Neuronpedia

    INDEX
    Explanations

    links or URLs within the text

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

    special characters and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Weiſe
    -0.76
    ஦
    -0.76
     Dieſe
    -0.75
    [@BOS@]
    -0.75
    <unused52>
    -0.75
    <unused17>
    -0.75
    <unused47>
    -0.75
    <unused41>
    -0.75
    <unused8>
    -0.75
    <unused16>
    -0.75
    POSITIVE LOGITS
     ***!
    0.34
     كومونز
    0.32
    __(/*!
    0.30
    Còn
    0.30
    ESTAMP
    0.28
    freude
    0.27
    Triple
    0.26
     ex
    0.26
     Paglinawan
    0.25
    mailto
    0.25
    Act Density 0.000%

    No Known Activations