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

    Neuronpedia

    INDEX
    Explanations

    C++ code generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     looking
    0.40
     going
    0.38
    लीज
    0.37
     তাল
    0.37
    navigate
    0.37
     Navigate
    0.35
    ();
    0.35
     hướng
    0.35
    Looking
    0.35
    єдна
    0.35
    POSITIVE LOGITS
     прибыль
    0.47
     ფედერ
    0.46
     feminist
    0.42
    GISLATIVE
    0.41
     çağ
    0.40
    แปล
    0.40
    casus
    0.39
    愷
    0.39
     причина
    0.39
     clairement
    0.39
    Act Density 0.000%

    No Known Activations