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

    Neuronpedia

    INDEX
    Explanations

    😊 emoji

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    특별시
    4.69
    ्स
    4.00
    aient
    3.44
    יות
    3.39
    aan
    3.16
    aa
    3.08
    THING
    3.06
    ação
    3.05
    jších
    2.98
    eers
    2.98
    POSITIVE LOGITS
    ী
    4.94
    ной
    2.89
    𝒆
    2.78
    는
    2.67
    ங்கிணை
    2.64
    ー
    2.64
    ੇ
    2.63
    ل
    2.58
    ور
    2.55
    व
    2.47
    Act Density 1.254%

    No Known Activations