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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    omial
    -0.07
    кадем
    -0.07
    ória
    -0.07
    (|
    -0.07
    /material
    -0.07
    >%
    -0.07
    ीसर
    -0.06
    _flat
    -0.06
    heritance
    -0.06
     мав
    -0.06
    POSITIVE LOGITS
    czas
    0.06
     it
    0.06
     clears
    0.06
     mission
    0.06
     belg
    0.06
     kaz
    0.06
     Jana
    0.06
     amen
    0.06
    염
    0.06
     instructional
    0.06
    Act Density 0.013%

    No Known Activations