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

    Neuronpedia

    INDEX
    Explanations

    Instructions and documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ineb
    -0.08
     natural
    -0.07
     natur
    -0.07
     tese
    -0.07
     בלתי
    -0.07
    ACK
    -0.07
     conject
    -0.07
     virtues
    -0.07
     decompress
    -0.07
     ilumin
    -0.07
    POSITIVE LOGITS
    设置
    0.13
     设置
    0.12
    設定
    0.12
     설정
    0.12
    =models
    0.11
     настройки
    0.11
    .upload
    0.11
     einstellen
    0.11
     настрой
    0.10
    配置
    0.10
    Act Density 0.064%

    No Known Activations