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

    Neuronpedia

    INDEX
    Explanations

    locations, services, and products

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     appunto
    0.33
    ।
    0.32
    গুলি
    0.31
    ।'
    0.29
    ።
    0.29
    ❔
    0.28
    um
    0.28
    ations
    0.28
    ों
    0.28
    ukset
    0.28
    POSITIVE LOGITS
    ड्रो
    0.37
    ۾
    0.37
     poseen
    0.35
     naszego
    0.32
     esposa
    0.32
    PhysRev
    0.32
     Eğer
    0.32
    PatientR
    0.32
     kalau
    0.32
     cárcel
    0.31
    Act Density 0.066%

    No Known Activations