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

    Neuronpedia

    INDEX
    Explanations

    version numbers (e.g., X.Y.Z)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    现
    0.38
     HUOBI
    0.37
     oranı
    0.37
     বয়স
    0.36
     USSR
    0.36
    ו
    0.35
     desenvolvido
    0.35
     berusia
    0.35
     biasa
    0.35
     usia
    0.35
    POSITIVE LOGITS
    de
    0.45
    aking
    0.41
    aña
    0.40
    eds
    0.40
     cordon
    0.39
    rowning
    0.38
    ander
    0.37
    edy
    0.37
    ede
    0.37
    er
    0.36
    Act Density 0.048%

    No Known Activations