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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (public
    -0.07
    �数
    -0.06
     ensued
    -0.06
     ensuing
    -0.06
     ego
    -0.06
    ापन
    -0.06
    ілі
    -0.06
    .Screen
    -0.06
     программ
    -0.06
    _annotations
    -0.06
    POSITIVE LOGITS
    اور
    0.07
    hardt
    0.07
     beh
    0.07
     준
    0.06
     Warp
    0.06
    НО
    0.06
    چ
    0.06
     відбу
    0.06
    kah
    0.06
     Casual
    0.06
    Act Density 0.006%

    No Known Activations