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

    Neuronpedia

    INDEX
    Explanations

    scientific methods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .definition
    -0.07
    .visit
    -0.07
     villages
    -0.07
     republican
    -0.06
    .Column
    -0.06
     ниже
    -0.06
     Flowers
    -0.06
     Vác
    -0.06
    elts
    -0.06
    سنگ
    -0.06
    POSITIVE LOGITS
    วด
    0.07
    الأ
    0.06
    additional
    0.06
     pine
    0.06
     archetype
    0.06
    oxid
    0.06
    irable
    0.06
     giảm
    0.06
     ^{°}
    0.06
    Contained
    0.06
    Act Density 0.004%

    No Known Activations