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

    Neuronpedia

    INDEX
    Explanations

    new object instantiation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Array
    0.47
     Array
    0.43
    लिया
    0.40
    Create
    0.39
     ar
    0.39
     Ar
    0.38
    Ar
    0.38
    Evaluate
    0.38
     controlling
    0.37
     lim
    0.37
    POSITIVE LOGITS
    𝒙
    0.43
    шымта
    0.40
     அதனால்
    0.38
    𝜁
    0.38
     совпада
    0.38
    芷
    0.38
     REGIUNI
    0.37
    𠃍
    0.37
    オク
    0.36
    鰐
    0.36
    Act Density 0.002%

    No Known Activations