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

    Neuronpedia

    INDEX
    Explanations

    education

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    顸
    -0.08
     Taste
    -0.08
     treats
    -0.08
     Смотр
    -0.07
    心仪的
    -0.07
    �
    -0.07
     Duke
    -0.07
    争
    -0.07
    不起
    -0.07
    评审
    -0.07
    POSITIVE LOGITS
     blackColor
    0.08
    .Byte
    0.08
    سياس
    0.07
     Alejandro
    0.07
     revelation
    0.07
    𝐩
    0.07
    מיקום
    0.07
    stanbul
    0.07
     '|
    0.07
     breathtaking
    0.07
    Act Density 0.028%

    No Known Activations