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

    Neuronpedia

    INDEX
    Explanations

    words and phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     both
    1.72
     one
    1.53
     with
    1.46
    iddle
    1.18
    タック
    1.18
    ensitive
    1.18
    idated
    1.13
    gressive
    1.13
     cheque
    1.12
     of
    1.12
    POSITIVE LOGITS
    rinsic
    3.79
    ответ
    3.63
    ات
    3.62
    s
    3.56
     сути
    3.53
    ۷
    3.51
    ٦
    3.46
    ٨
    3.45
    7
    3.45
    ٧
    3.44
    Act Density 0.597%

    No Known Activations