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

    Neuronpedia

    INDEX
    Explanations

    closing tags in HTML code

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

    HTML tags and links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    rungsseite
    -1.09
    脚注の使い方
    -1.00
    <unused41>
    -0.95
    <unused28>
    -0.95
    <unused74>
    -0.95
    <unused52>
    -0.95
    <unused14>
    -0.95
    <unused3>
    -0.94
    [@BOS@]
    -0.94
    <pad>
    -0.94
    POSITIVE LOGITS
    .
    0.33
     complètes
    0.31
    //
    0.29
    ltä
    0.29
    '.
    0.28
    /*
    0.28
     detuvo
    0.27
    P
    0.26
    D
    0.25
    it
    0.24
    Act Density 0.011%

    No Known Activations