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

    Neuronpedia

    INDEX
    Explanations

    Foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     "-
    -0.08
     Auschwitz
    -0.07
     '-
    -0.07
    Joseph
    -0.07
    Washington
    -0.07
     Best
    -0.07
    egative
    -0.06
     FormData
    -0.06
    pairs
    -0.06
    >-
    -0.06
    POSITIVE LOGITS
     チ
    0.08
     داشته
    0.07
     �
    0.07
     حي
    0.06
     mož
    0.06
    �
    0.06
     proposing
    0.06
     ASC
    0.06
         
↵
    0.06
    どこ
    0.06
    Act Density 0.110%

    No Known Activations