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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating examples or explanations

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

    introduces examples or explanations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SequentialGroup
    -0.53
    uxxxx
    -0.52
     transfieras
    -0.49
    ViewFeatures
    -0.47
    EndContext
    -0.47
     ModelExpression
    -0.46
     testigos
    -0.46
     otomatig
    -0.45
    findpost
    -0.44
     nalazi
    -0.43
    POSITIVE LOGITS
    rungsseite
    0.59
    :✨
    0.54
    UpInside
    0.48
     pod
    0.47
    AndEndTag
    0.43
    şört
    0.42
    &__
    0.41
    InlineData
    0.40
    
    0.39
     Pip
    0.38
    Act Density 0.261%

    No Known Activations