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

    Neuronpedia

    INDEX
    Explanations

    sample

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🌶
    -0.07
    许可证
    -0.07
    챌
    -0.07
    支线任务
    -0.07
    �
    -0.07
    ()].
    -0.07
     여기
    -0.06
     templates
    -0.06
    ⛺
    -0.06
    𝑽
    -0.06
    POSITIVE LOGITS
    -friendly
    0.07
    נה
    0.07
    sit
    0.07
    eut
    0.07
    ach
    0.07
    wart
    0.07
     North
    0.07
    ocks
    0.07
    stein
    0.06
    龙
    0.06
    Act Density 0.013%

    No Known Activations