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

    Neuronpedia

    INDEX
    Explanations

    a summary of data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ocompat
    0.88
    atonic
    0.88
     ㅛ
    0.83
    ചര്യ
    0.82
     Fähigkeiten
    0.82
     सिखा
    0.82
    elajaran
    0.81
     psic
    0.80
     امتحان
    0.79
     Reject
    0.78
    POSITIVE LOGITS
     data
    2.44
     statistics
    2.10
    data
    2.09
    数据
    2.07
    数据的
    2.06
     데이터
    2.04
    データ
    2.02
    データを
    2.00
    データの
    2.00
     Data
    1.99
    Act Density 0.911%

    No Known Activations