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

    Neuronpedia

    INDEX
    Explanations

    including or excluding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nance
    0.71
    LogLevel
    0.69
     tần
    0.68
    Wage
    0.68
     высокую
    0.68
    getBalance
    0.68
     দামে
    0.67
     হারে
    0.65
    度に
    0.65
     hohe
    0.64
    POSITIVE LOGITS
     including
    2.59
    Including
    2.50
    including
    2.44
     Including
    2.43
     incluindo
    2.35
     excluding
    2.28
    包括
    2.19
     INCLUDING
    2.18
     включая
    2.18
    excluding
    2.16
    Act Density 0.626%

    No Known Activations