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

    Neuronpedia

    INDEX
    Explanations

    references to neutrality in various contexts

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

    concept of neutral

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Astrophysics
    -0.46
    fstream
    -0.46
     SqlCommand
    -0.45
    Datei
    -0.43
     getFile
    -0.41
    fbox
    -0.41
    DotNetBar
    -0.40
    Lesen
    -0.40
     getAge
    -0.39
    figs
    -0.39
    POSITIVE LOGITS
     neutral
    2.38
     Neutral
    2.34
    neutral
    2.31
    Neutral
    2.27
    UTRAL
    1.80
     нейтра
    1.77
     neutrality
    1.77
     neutre
    1.70
     neutrals
    1.68
     Neutr
    1.52
    Act Density 0.004%

    No Known Activations