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

    Neuronpedia

    INDEX
    Explanations

    references to specific protocols or technical terms in various contexts

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    programming terms in multiple languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    دانشنامهٔ
    -1.25
     pinulongan
    -0.97
     فريبيس
    -0.95
    ^(@)
    -0.81
     itſelf
    -0.80
     سكانية
    -0.80
     myſelf
    -0.77
     stiefel
    -0.77
     tfsi
    -0.77
    alakip
    -0.76
    POSITIVE LOGITS
     „
    0.68
     «
    0.68
    <bos>
    0.61
    «
    0.60
    »
    0.60
    „
    0.57
    （
    0.54
    ：
    0.53
    「
    0.53
    。
    0.53
    Act Density 0.105%

    No Known Activations