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

    Neuronpedia

    INDEX
    Explanations

    ."

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Silence
    -0.07
     ange
    -0.07
     approach
    -0.07
     Created
    -0.07
    ]).
    -0.07
    {'
    -0.06
    -extension
    -0.06
     начале
    -0.06
     agile
    -0.06
     mec
    -0.06
    POSITIVE LOGITS
    ">'↵
    0.06
     glor
    0.06
     Flo
    0.06
     Dwight
    0.06
    Clearly
    0.06
    :'',↵
    0.06
     земель
    0.06
    絵
    0.06
     [...]↵↵
    0.06
                    ↵↵
    0.06
    Act Density 0.044%

    No Known Activations