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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    බ
    -0.08
    נק
    -0.08
     Prem
    -0.08
    施策
    -0.07
    哺乳
    -0.07
    𝙍
    -0.07
     configur
    -0.07
    中华文化
    -0.07
    ツ
    -0.07
     login
    -0.07
    POSITIVE LOGITS
     ומה
    0.08
    ,double
    0.08
    )get
    0.07
    ,sum
    0.07
    十大
    0.07
    ename
    0.07
     guest
    0.07
     sustainable
    0.07
     ))
    0.06
     procedural
    0.06
    Act Density 0.087%

    No Known Activations