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

    Neuronpedia

    INDEX
    Explanations

    solving problems

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -blood
    -0.07
    <↵
    -0.07
    eiß
    -0.06
     עסק
    -0.06
    宪
    -0.06
     gentlemen
    -0.06
    >
↵
↵
↵
    -0.06
    剡
    -0.06
    主角
    -0.06
     Scout
    -0.06
    POSITIVE LOGITS
    icon
    0.07
    �
    0.07
    side
    0.07
    初始化
    0.07
     shortcut
    0.07
    下
    0.07
    holes
    0.07
    favor
    0.07
     plugins
    0.07
     upload
    0.07
    Act Density 0.095%

    No Known Activations