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

    Neuronpedia

    INDEX
    Explanations

    tree planting or license

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.52
     /=
    0.44
    7
    0.43
    にお
    0.42
    8
    0.42
    6
    0.42
     에너지
    0.41
     Agreement
    0.41
    9
    0.41
     Objectives
    0.40
    POSITIVE LOGITS
    ة
    0.50
    ﺔ
    0.48
    }.")
    0.46
    ím
    0.45
     nhiêu
    0.45
     participle
    0.45
    ме
    0.44
    éph
    0.44
    ड़ी
    0.44
    σης
    0.44
    Act Density 0.000%

    No Known Activations