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

    Neuronpedia

    INDEX
    Explanations

    conscientious objectors, workers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     unnamed
    -0.08
    ama
    -0.07
    ��
    -0.07
     sung
    -0.07
    	setState
    -0.07
    ук
    -0.07
    먕
    -0.07
    aged
    -0.06
    identified
    -0.06
    ила
    -0.06
    POSITIVE LOGITS
    切尔
    0.08
    ////////////////////////////////////////////////////////////////////////////////
    0.07
    酋
    0.07
    定制
    0.07
    措
    0.07
    ра
    0.07
    万亿元
    0.07
    契
    0.07
    tracking
    0.07
    .exe
    0.06
    Act Density 0.001%

    No Known Activations