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

    Neuronpedia

    INDEX
    Explanations

    advising caution

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     dolayı
    0.52
     이해
    0.46
    Kerry
    0.45
    합니다
    0.44
     capire
    0.44
    dır
    0.42
     طریقے
    0.42
    และ
    0.42
    य
    0.42
    судар
    0.42
    POSITIVE LOGITS
    '
    0.49
    ug
    0.45
    in
    0.42
     جيڪ
    0.39
    uc
    0.39
     steeply
    0.39
    哪些
    0.38
     සහිත
    0.38
     εμφαν
    0.38
    uf
    0.38
    Act Density 0.057%

    No Known Activations