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

    Neuronpedia

    INDEX
    Explanations

    limitations and choices

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Fu
    -0.07
    loadModel
    -0.06
     strftime
    -0.06
    ура
    -0.06
    DDR
    -0.06
    porno
    -0.06
     aroma
    -0.06
     Ağ
    -0.06
    enders
    -0.06
     Aura
    -0.06
    POSITIVE LOGITS
     delight
    0.07
    .SUCCESS
    0.07
     Đài
    0.06
    _neighbors
    0.06
    .Tags
    0.06
     próp
    0.06
    (left
    0.06
    itian
    0.06
     associ
    0.06
     milionů
    0.06
    Act Density 0.024%

    No Known Activations