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

    Neuronpedia

    INDEX
    Explanations

    use changes and practices

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    questa
    0.49
    tug
    0.47
    mét
    0.46
    hotels
    0.45
    sistema
    0.43
    separate
    0.43
    lisi
    0.42
    lifts
    0.42
    amera
    0.42
     Metabolism
    0.42
    POSITIVE LOGITS
     represented
    0.56
     rappresenta
    0.55
     represents
    0.50
     represent
    0.49
     repressive
    0.49
    Durante
    0.46
     championed
    0.46
     neka
    0.46
     rappresent
    0.46
     bravely
    0.45
    Act Density 0.000%

    No Known Activations