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

    Neuronpedia

    INDEX
    Explanations

    parts of the text that denote high values, suggesting a focus on significant data or key concepts

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

    there is a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TextAppearance
    -0.41
    ValueStyle
    -0.38
     kaynağından
    -0.36
    EDEFAULT
    -0.35
    HostException
    -0.35
    |};
    -0.35
    ectoria
    -0.34
    ionage
    -0.34
    toThrow
    -0.34
    Personendaten
    -0.33
    POSITIVE LOGITS
    ⓧ
    0.57
    ंदीखरीदारी
    0.54
     ролях
    0.48
     MenuView
    0.47
     stöd
    0.46
     transactions
    0.46
     ilustrasi
    0.45
    قایناق‌لار
    0.42
     övers
    0.42
     Wilayah
    0.41
    Act Density 0.004%

    No Known Activations