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

    Neuronpedia

    INDEX
    Explanations

    caffeine/stimulants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itt
    -0.07
    领跑
    -0.07
    큼
    -0.07
     Achie
    -0.07
     GM
    -0.06
     Fixture
    -0.06
    점
    -0.06
     scored
    -0.06
     Achievement
    -0.06
     développement
    -0.06
    POSITIVE LOGITS
    _sd
    0.07
    慵
    0.07
    堵塞
    0.07
    orro
    0.07
     terrified
    0.07
     salvar
    0.06
    (binary
    0.06
    路过
    0.06
     שצריך
    0.06
     enclosed
    0.06
    Act Density 0.029%

    No Known Activations