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

    Neuronpedia

    INDEX
    Explanations

    json formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    othelial
    0.22
    aeskeygenassist
    0.22
    iladi
    0.22
    ‌്
    0.21
    rawberry
    0.21
    岁月
    0.21
    slidesPerGroup
    0.21
    र्डिनेट
    0.21
    ༌
    0.21
    aterData
    0.20
    POSITIVE LOGITS
     Energies
    0.21
     Euros
    0.20
     行
    0.20
     HP
    0.19
     compl
    0.19
     Primarily
    0.19
     HPC
    0.19
     Freed
    0.19
     Dollars
    0.19
    Ports
    0.19
    Act Density 0.100%

    No Known Activations