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

    Neuronpedia

    INDEX
    Explanations

    before

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ассив
    -0.08
    eload
    -0.07
    環
    -0.07
    ấc
    -0.07
    _CONSTANT
    -0.07
    buttons
    -0.06
    sts
    -0.06
    缩
    -0.06
    رانی
    -0.06
    chars
    -0.06
    POSITIVE LOGITS
     Jonathan
    0.07
     حقوق
    0.07
    0.07
     B
    0.06
     _↵
    0.06
    BST
    0.06
    ิเวณ
    0.06
     котором
    0.06
    _PRIVATE
    0.06
    elder
    0.06
    Act Density 0.000%

    No Known Activations