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

    Neuronpedia

    INDEX
    Explanations

    in role

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    }&=
    0.47
    M
    0.46
     &=&
    0.45
      
    0.44
     rind
    0.43
     sich
    0.42
     t
    0.42
     b
    0.42
     VERT
    0.41
     roadside
    0.40
    POSITIVE LOGITS
    娜
    0.53
    champion
    0.50
     normales
    0.46
    actifs
    0.46
     انجن
    0.45
    ovenant
    0.45
    ाइड
    0.43
    즌
    0.43
    وین
    0.43
     سکتی
    0.43
    Act Density 0.001%

    No Known Activations