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

    Neuronpedia

    INDEX
    Explanations

    story requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     defiance
    1.57
     Archaeological
    1.55
     sparring
    1.53
     tỉnh
    1.52
     promulg
    1.51
     felic
    1.48
    কী
    1.48
     succinct
    1.48
     festivals
    1.45
     conversational
    1.44
    POSITIVE LOGITS
    id
    2.02
    ي
    1.96
    ่า
    1.93
    ij
    1.85
    r
    1.83
    ik
    1.80
    rä
    1.76
    ill
    1.73
    arc
    1.71
    ak
    1.67
    Act Density 0.136%

    No Known Activations