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

    Neuronpedia

    INDEX
    Explanations

    code-related entities or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     وبين
    0.71
    ↵
    0.68
     FIXME
    0.65
    где
    0.65
    га
    0.64
    邝
    0.64
     temu
    0.63
     Frankel
    0.63
    ،
    0.63
     ensue
    0.63
    POSITIVE LOGITS
    ﺎ
    0.89
    3
    0.87
    7
    0.86
    2
    0.86
    4
    0.85
    1
    0.84
    5
    0.84
    9
    0.83
    𝐴
    0.79
    8
    0.78
    Act Density 0.001%

    No Known Activations