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

    Neuronpedia

    INDEX
    Explanations

    agent or cause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    기
    0.43
    ले
    0.41
     lossless
    0.40
    υ
    0.40
    лі
    0.39
    ку
    0.38
    ين
    0.38
    le
    0.37
     rectifier
    0.37
    ع
    0.36
    POSITIVE LOGITS
     by
    0.50
     from
    0.45
            
    0.43
    ator
    0.42
     at
    0.42
     মূলত
    0.39
    people
    0.39
     aka
    0.39
     Own
    0.39
    heroes
    0.38
    Act Density 0.065%

    No Known Activations