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

    Neuronpedia

    INDEX
    Explanations

    calendar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trip
    -0.07
    Foo
    -0.07
    Trip
    -0.06
     Trip
    -0.06
     arterial
    -0.06
     satisfies
    -0.06
     (_
    -0.06
    xdb
    -0.06
     auditing
    -0.06
     Biology
    -0.06
    POSITIVE LOGITS
    يلي
    0.07
    001
    0.06
     đài
    0.06
    	dx
    0.06
    094
    0.06
    -pos
    0.06
    DIST
    0.06
    機
    0.06
     Mädchen
    0.06
    \Exception
    0.06
    Act Density 0.003%

    No Known Activations