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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating contrast or comparison

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

    "too"

    np_acts-logits-general · gemini-2.0-flash

    adding emphasis or inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    stdc
    -0.81
    Personensuche
    -0.69
     Ceinture
    -0.66
    InitVars
    -0.64
    ViewInit
    -0.63
     betweenstory
    -0.63
     ModelRenderer
    -0.62
    TypedDataSet
    -0.62
     JADX
    -0.61
     newBuilder
    -0.61
    POSITIVE LOGITS
     esterni
    0.80
    たまた
    0.79
     kasarigan
    0.74
     zwar
    0.66
    fortawesome
    0.65
     שוליים
    0.63
     חיצוניים
    0.60
    즉
    0.58
    </i>
    0.57
    amie
    0.56
    Act Density 1.417%

    No Known Activations