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

    Neuronpedia

    INDEX
    Explanations

    asm

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ﭹ
    -0.08
     teaches
    -0.08
     chaque
    -0.07
    (cm
    -0.07
     các
    -0.07
    .cur
    -0.07
    收費
    -0.07
     Vs
    -0.07
    相比于
    -0.07
    起码
    -0.07
    POSITIVE LOGITS
    DL
    0.07
     Access
    0.07
    _PTR
    0.07
    Ջ
    0.07
    (output
    0.06
    뙇
    0.06
     sodium
    0.06
    (drop
    0.06
    除尘
    0.06
     Defines
    0.06
    Act Density 0.001%

    No Known Activations