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

    Neuronpedia

    INDEX
    Explanations

    acceptance of terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    まったく
    0.45
     "))
    0.43
    0.43
    जनिक
    0.42
     són
    0.42
    الغ
    0.41
     solely
    0.41
    불
    0.40
     coldly
    0.40
    ただ
    0.40
    POSITIVE LOGITS
    Checkbox
    0.50
    Wise
    0.46
    requirement
    0.44
     উই
    0.44
    Simple
    0.41
     اصول
    0.41
    Valid
    0.41
    aisu
    0.41
     ಕೈ
    0.40
    Need
    0.40
    Act Density 0.000%

    No Known Activations