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

    Neuronpedia

    INDEX
    Explanations

    design and defines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    いた
    2.03
    t
    1.92
    IE
    1.73
    ள்ளது
    1.72
    ING
    1.70
    賁
    1.70
    ten
    1.69
    IA
    1.69
    동안
    1.69
    }
    1.63
    POSITIVE LOGITS
    ни
    2.67
    েও
    2.19
     contar
    1.80
     Vý
    1.75
     velike
    1.72
    scapes
    1.70
     payoffs
    1.70
     postulates
    1.67
     avanzar
    1.66
     computadora
    1.64
    Act Density 0.792%

    No Known Activations