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

    Neuronpedia

    INDEX
    Explanations

    policy id and pygame code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     다섯
    0.24
    ésie
    0.24
     giphy
    0.23
     बर्तन
    0.23
     Moistur
    0.23
     δύο
    0.22
    𝟑
    0.22
     Jésus
    0.21
     下さい
    0.21
    Nursing
    0.21
    POSITIVE LOGITS
    io
    0.26
    class
    0.24
    it
    0.23
    al
    0.23
     specialized
    0.23
     we
    0.22
    im
    0.22
    able
    0.22
            
    0.22
              
    0.21
    Act Density 0.078%

    No Known Activations