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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    illard
    -0.08
    แข
    -0.08
     contender
    -0.07
     holders
    -0.07
     nueva
    -0.06
    Univers
    -0.06
    istency
    -0.06
    вшего
    -0.06
    ---↵
    -0.06
    Debugger
    -0.06
    POSITIVE LOGITS
     statistics
    0.08
    oralType
    0.07
    ;;;;;;;;
    0.07
    حال
    0.07
     Бо
    0.07
    처리
    0.07
     رسالة
    0.07
    زراعة
    0.07
     קשה
    0.07
    ")))
    0.07
    Act Density 0.004%

    No Known Activations