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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <Document
    -0.08
     conduc
    -0.07
    携
    -0.07
    .sidebar
    -0.07
    ecture
    -0.07
    OUND
    -0.07
     этому
    -0.07
    reation
    -0.07
     pos
    -0.07
     Preserve
    -0.07
    POSITIVE LOGITS
     obligated
    0.07
    ///↵
    0.07
     Wes
    0.07
    吃惊
    0.06
     conson
    0.06
     wrath
    0.06
    毫不犹豫
    0.06
    normalized
    0.06
    基础上
    0.06
    warehouse
    0.06
    Act Density 0.001%

    No Known Activations