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

    Neuronpedia

    INDEX
    Explanations

    Installing software packages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Inter
    -0.07
    from
    -0.07
     textbooks
    -0.07
    lement
    -0.06
    -tax
    -0.06
    important
    -0.06
    иш
    -0.06
    Hospital
    -0.06
    Embedded
    -0.06
    	class
    -0.06
    POSITIVE LOGITS
     스타
    0.07
    ümü
    0.07
    CEEDED
    0.07
     Assault
    0.06
     Braun
    0.06
     ภาษ
    0.06
    幻
    0.06
     الجم
    0.06
    분석
    0.06
     disappointment
    0.06
    Act Density 0.044%

    No Known Activations