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

    Neuronpedia

    INDEX
    Explanations

    uploading files and data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۲
    1.01
    ২
    0.95
    of
    0.94
    sobre
    0.93
    ৩৩
    0.93
     کاهش
    0.89
    ۳
    0.89
    یت
    0.89
    siswa
    0.89
    dalam
    0.87
    POSITIVE LOGITS
     upload
    1.39
     Upload
    1.23
    '
    1.21
     uploading
    1.18
    ↵
    1.16
    P
    1.16
     uploaded
    1.15
     uploads
    1.11
    in
    1.09
    B
    1.09
    Act Density 0.016%

    No Known Activations