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

    Neuronpedia

    INDEX
    Explanations

    FROM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    商户
    -0.07
     junction
    -0.07
     Melbourne
    -0.07
    桃
    -0.06
     expressive
    -0.06
    单项
    -0.06
     Hello
    -0.06
    氯
    -0.06
    Mob
    -0.06
    渠
    -0.06
    POSITIVE LOGITS
    -dem
    0.07
    趋于
    0.07
    -get
    0.07
    👺
    0.07
    baseUrl
    0.06
    _need
    0.06
     données
    0.06
     ├──
    0.06
     snprintf
    0.06
    ⟶
    0.06
    Act Density 0.012%

    No Known Activations