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

    Neuronpedia

    INDEX
    Explanations

    OpenAI chat and text completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    (../
    0.39
     ერთი
    0.39
    Frag
    0.39
     해
    0.38
    ([\
    0.38
    ുമോ
    0.38
    lahir
    0.38
    特集
    0.38
     Oldborough
    0.38
    銨
    0.38
    POSITIVE LOGITS
     फॉर
    0.36
     for
    0.35
     FOR
    0.35
     Heading
    0.35
     stateMutability
    0.35
     Text
    0.34
    =?
    0.33
     sheet
    0.33
     event
    0.32
     journal
    0.32
    Act Density 0.002%

    No Known Activations