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

    Neuronpedia

    INDEX
    Explanations

    boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    K
    0.87
    BAB
    0.73
    B
    0.73
    Perry
    0.68
    Glasgow
    0.68
    К
    0.68
    s
    0.67
    R
    0.66
    sG
    0.65
    Kirk
    0.65
    POSITIVE LOGITS
    en
    0.94
     boundaries
    0.83
    ท์
    0.81
    ing
    0.75
    oit
    0.70
    :
    0.69
     comunicación
    0.67
    ंसाठी
    0.67
    enol
    0.65
     «
    0.64
    Act Density 0.015%

    No Known Activations