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

    Neuronpedia

    INDEX
    Explanations

    supercooling

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Amsterdam
    -0.08
     사업
    -0.07
     affine
    -0.07
    甥
    -0.06
    zen
    -0.06
     עצמי
    -0.06
    春天
    -0.06
    疏散
    -0.06
     responseBody
    -0.06
    葳
    -0.06
    POSITIVE LOGITS
    LABEL
    0.08
    0.07
     الجمه
    0.07
    多个国家
    0.07
    %"
    0.07
    рук
    0.07
    lates
    0.07
    뀜
    0.06
    omet
    0.06
     CPUs
    0.06
    Act Density 0.001%

    No Known Activations