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

    Neuronpedia

    INDEX
    Explanations

    Non-English text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     How
    -0.07
    hů
    -0.06
    ython
    -0.06
     конф
    -0.06
     sơ
    -0.06
    ARY
    -0.06
     thus
    -0.06
     đổ
    -0.06
    _hostname
    -0.06
    total
    -0.06
    POSITIVE LOGITS
     muit
    0.10
     많은
    0.08
     demasi
    0.08
    ParticleSystem
    0.07
    増
    0.07
    すぎ
    0.07
    少
    0.07
     Baghdad
    0.07
     banyak
    0.07
    Magn
    0.07
    Act Density 0.024%

    No Known Activations