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

    Neuronpedia

    INDEX
    Explanations

    Technical forum posts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hus
    -0.07
    	pid
    -0.07
    퓶
    -0.06
    ANCELED
    -0.06
     swój
    -0.06
    iah
    -0.06
    POR
    -0.06
    maybe
    -0.06
     �
    -0.06
    _heat
    -0.06
    POSITIVE LOGITS
    unta
    0.07
     ListView
    0.07
    实习
    0.07
    оль
    0.07
    桌面
    0.07
    verbatim
    0.07
     playlists
    0.07
    /accounts
    0.07
    שיבה
    0.07
    models
    0.06
    Act Density 0.002%

    No Known Activations