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

    Neuronpedia

    INDEX
    Explanations

    Mach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ipt
    -0.07
    련
    -0.06
    偲
    -0.06
    ḃ
    -0.06
    .Properties
    -0.06
    -rights
    -0.06
    討論
    -0.06
    𝗮
    -0.06
     troll
    -0.06
     đảm
    -0.06
    POSITIVE LOGITS
     nominal
    0.07
    центр
    0.07
    刘
    0.07
     문자
    0.07
    =img
    0.07
    FFE
    0.07
     ASAP
    0.06
    是一种
    0.06
    атегор
    0.06
    🌴
    0.06
    Act Density 0.005%

    No Known Activations