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

    Neuronpedia

    INDEX
    Explanations

    Period

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مكان
    -0.07
    ตะ
    -0.07
    leigh
    -0.07
    嘿嘿
    -0.07
    (mouse
    -0.07
    舒适的
    -0.06
    Oper
    -0.06
    稑
    -0.06
    .expect
    -0.06
     który
    -0.06
    POSITIVE LOGITS
    짊
    0.07
    -s
    0.07
    ées
    0.06
     referencedColumnName
    0.06
    Das
    0.06
     dumped
    0.06
    .parseColor
    0.06
     biç
    0.06
    =null
    0.06
    оч
    0.06
    Act Density 0.005%

    No Known Activations