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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and data types

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

    user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.63
     يتيمه
    -0.59
     سكانية
    -0.56
    Бахар
    -0.55
    Personensuche
    -0.54
    WebVitals
    -0.54
    ThroughAttribute
    -0.53
     Jefus
    -0.52
    TintMode
    -0.51
    inghouse
    -0.51
    POSITIVE LOGITS
    ::
    0.89
    fjspx
    0.67
    <bos>
    0.48
     ::
    0.48
    :::
    0.45
    >::
    0.44
    SequentialGroup
    0.44
    ::{
    0.42
    ::::
    0.39
     wildest
    0.38
    Act Density 0.000%

    No Known Activations