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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🐂
    -0.08
    ورد
    -0.07
    𝙈
    -0.06
    ㆍ
    -0.06
    ⤇
    -0.06
    🥮
    -0.06
    &,
    -0.06
     problems
    -0.06
    ﲪ
    -0.06
    쑹
    -0.06
    POSITIVE LOGITS
    	can
    0.07
    getY
    0.07
     jail
    0.07
    -destruct
    0.07
     Servers
    0.07
    を入れ
    0.07
    電子郵件
    0.06
    殄
    0.06
     shoreline
    0.06
    profits
    0.06
    Act Density 0.047%

    No Known Activations