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

    Neuronpedia

    INDEX
    Explanations

    Math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    起来
    -0.07
    xcb
    -0.07
     ally
    -0.07
     elseif
    -0.07
     whisk
    -0.06
    Ẽ
    -0.06
    vox
    -0.06
    (field
    -0.06
    -Jan
    -0.06
    	sum
    -0.06
    POSITIVE LOGITS
     Wisconsin
    0.07
     sophisticated
    0.07
    专业
    0.07
    密切相关
    0.07
     Hollow
    0.07
    ʽ
    0.07
    San
    0.07
     consolidated
    0.07
    高层次
    0.07
    骆
    0.07
    Act Density 0.003%

    No Known Activations