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

    Neuronpedia

    INDEX
    Explanations

    numbers and dates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Model
    -0.07
    मक
    -0.07
    _int
    -0.07
     roof
    -0.07
    Arizona
    -0.06
     GMT
    -0.06
    직
    -0.06
     tunnel
    -0.06
     patrons
    -0.06
    �藏
    -0.06
    POSITIVE LOGITS
    .....↵↵
    0.06
    Certificates
    0.06
     mělo
    0.06
    的问题
    0.06
     hotelu
    0.06
    323
    0.06
     scrut
    0.06
     söyledi
    0.06
     contag
    0.06
     类
    0.06
    Act Density 0.066%

    No Known Activations