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

    Neuronpedia

    INDEX
    Explanations

    Accessory

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lers
    -0.07
    프로그
    -0.06
    ]:↵↵↵
    -0.06
     sessions
    -0.06
    Wat
    -0.06
    .lab
    -0.06
    itle
    -0.06
    롭
    -0.06
     Hotels
    -0.06
    _Reference
    -0.06
    POSITIVE LOGITS
    安全隐患
    0.08
     POINTER
    0.07
     thánh
    0.07
     buffer
    0.07
     PEOPLE
    0.07
    管
    0.07
     diferença
    0.07
    中途
    0.07
     الطفل
    0.07
     CHILD
    0.07
    Act Density 0.005%

    No Known Activations