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

    Neuronpedia

    INDEX
    Explanations

    code errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    interop
    -0.07
    ��
    -0.07
     mnohem
    -0.07
     withd
    -0.06
     vữ
    -0.06
     násled
    -0.06
    atas
    -0.06
     커
    -0.06
     nog
    -0.06
     Рег
    -0.06
    POSITIVE LOGITS
    ategorias
    0.07
    Experiment
    0.07
    OTOS
    0.06
    еи
    0.06
    yı
    0.06
     Appliances
    0.06
    ké
    0.06
    stab
    0.06
    Concern
    0.06
    UPDATED
    0.06
    Act Density 0.002%

    No Known Activations