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

    Neuronpedia

    INDEX
    Explanations

    technical processes

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    checked
    0.61
    Lead
    0.59
    ヤ
    0.59
    タ
    0.57
     télécharg
    0.56
    Earl
    0.56
    ワン
    0.55
    ڈی
    0.55
    Gone
    0.55
    Contin
    0.54
    POSITIVE LOGITS
    حال
    0.79
     حال
    0.73
     tempHeader
    0.68
    成绩
    0.66
    ୌ
    0.66
     photocurrent
    0.63
    stoffen
    0.63
     Điện
    0.62
     нынеш
    0.62
    работ
    0.61
    Act Density 0.001%

    No Known Activations