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

    Neuronpedia

    INDEX
    Explanations

    specific items or categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mää
    1.29
    শিয়া
    1.24
    1.20
    зация
    1.19
     presenter
    1.19
    ექს
    1.16
     opposit
    1.16
    alya
    1.15
     Bö
    1.14
     sabi
    1.12
    POSITIVE LOGITS
    MENTS
    1.11
    ees
    1.11
     Nipp
    1.09
     trick
    1.08
     проблемой
    1.07
    റ
    1.06
     Trick
    1.05
    {}",
    1.05
     troubleshoot
    1.02
    ma
    1.02
    Act Density 0.000%

    No Known Activations