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

    Neuronpedia

    INDEX
    Explanations

    xs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    MF
    -0.07
    Tour
    -0.07
    (Point
    -0.06
    Contains
    -0.06
    تضمن
    -0.06
    *z
    -0.06
    מית
    -0.06
     mặt
    -0.06
    را
    -0.06
     منها
    -0.06
    POSITIVE LOGITS
    ">-->↵
    0.08
     insignificant
    0.07
    }];↵
    0.07
    捍
    0.07
    ڰ
    0.07
    >-->↵
    0.06
    _LANG
    0.06
     //}↵
    0.06
    ⻁
    0.06
     restarted
    0.06
    Act Density 0.001%

    No Known Activations