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

    Neuronpedia

    INDEX
    Explanations

    colons or quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Patients
    -0.07
    _FRAMEBUFFER
    -0.06
    Bed
    -0.06
    "default
    -0.06
     eh
    -0.06
    urning
    -0.06
    ÜR
    -0.06
    Phones
    -0.06
    ociety
    -0.06
     najczęściej
    -0.06
    POSITIVE LOGITS
    坜
    0.07
    brook
    0.06
    넢
    0.06
    اظ
    0.06
    ויד
    0.06
    北京市
    0.06
    悅
    0.06
    缎
    0.06
     scal
    0.06
    �
    0.06
    Act Density 0.019%

    No Known Activations