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

    Neuronpedia

    INDEX
    Explanations

    counting occurrences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chová
    -0.75
    】
    -0.73
     schoolchildren
    -0.72
     هن
    -0.69
    }}(
    -0.69
    兆
    -0.68
    ۔
    -0.68
     cechy
    -0.67
    quinone
    -0.67
     personalidad
    -0.67
    POSITIVE LOGITS
    [:]
    1.44
    (*)
    1.16
     (_)
    1.03
     (*)
    0.96
    (:)
    0.95
     [*]
    0.94
    [*]
    0.94
    <?>
    0.92
     (-)
    0.90
    [:
    0.89
    Act Density 0.090%

    No Known Activations