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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ix
    -0.07
    גוש
    -0.07
    。”↵↵
    -0.07
     hann
    -0.07
    fontsize
    -0.06
    裂缝
    -0.06
    街区
    -0.06
    ꪀ
    -0.06
    人群中
    -0.06
    تفسير
    -0.06
    POSITIVE LOGITS
    }"
    0.08
    设定
    0.08
     Control
    0.07
     awarded
    0.07
    奔驰
    0.07
     lower
    0.07
     fw
    0.07
    铃
    0.07
     EQUI
    0.07
     Cover
    0.07
    Act Density 0.009%

    No Known Activations