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

    Neuronpedia

    INDEX
    Explanations

    modelparameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ěz
    0.41
    得多
    0.38
    τυ
    0.38
    ResponseBody
    0.37
     Shortly
    0.37
     ví
    0.36
     موفق
    0.36
     Partially
    0.36
    \|^{
    0.36
    ទាំង
    0.36
    POSITIVE LOGITS
    シス
    0.38
    parameter
    0.36
     beverages
    0.35
     abstraction
    0.35
     omission
    0.35
    భు
    0.34
    רג
    0.34
     imaginary
    0.34
     omitting
    0.33
     unavailability
    0.33
    Act Density 0.024%

    No Known Activations