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

    Neuronpedia

    INDEX
    Explanations

    know

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Q
    -0.08
    类似于
    -0.08
    _PRE
    -0.07
     Ecc
    -0.07
     Kind
    -0.07
    cmds
    -0.07
    锑
    -0.07
     شب
    -0.07
    谢谢
    -0.07
    .square
    -0.07
    POSITIVE LOGITS
     víctima
    0.07
    robot
    0.07
    た
    0.07
    unte
    0.07
    Initial
    0.07
    'n
    0.07
    冬奥
    0.07
    kin
    0.07
    	core
    0.06
    Conversation
    0.06
    Act Density 0.012%

    No Known Activations