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

    Neuronpedia

    INDEX
    Explanations

    references to versioning in software or API specifications

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

    api version specifiers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ویکی‌پدیای
    -0.54
    SequentialGroup
    -0.54
     anſ
    -0.53
     ſche
    -0.53
    BeginContext
    -0.53
     myſelf
    -0.49
     Réponses
    -0.49
    
    -0.49
     uſed
    -0.48
     lenker
    -0.47
    POSITIVE LOGITS
    v
    0.52
     v
    0.51
    :✨
    0.42
    NameInMap
    0.41
    ISupport
    0.41
    twimg
    0.41
     خار
    0.40
    setTimestamp
    0.39
    ouch
    0.37
    RegressionTest
    0.36
    Act Density 0.009%

    No Known Activations