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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .checked
    -0.07
    .pageX
    -0.06
    具体情况
    -0.06
     vatanda
    -0.06
    党史
    -0.06
    续航
    -0.06
    ﺫ
    -0.06
    市场需求
    -0.06
     фа
    -0.06
     obedient
    -0.06
    POSITIVE LOGITS
     bảng
    0.07
    氚
    0.07
     haciendo
    0.07
    람
    0.07
    忽略了
    0.07
    ("""↵
    0.07
     точно
    0.07
    🌎
    0.06
     Thần
    0.06
     Cork
    0.06
    Act Density 0.032%

    No Known Activations