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

    Neuronpedia

    INDEX
    Explanations

    describes things as lifelike

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    вите
    0.53
    ▆
    0.48
    média
    0.48
    是
    0.47
    seater
    0.47
    ানের
    0.46
     mérid
    0.46
    陶
    0.46
    torch
    0.45
    starch
    0.45
    POSITIVE LOGITS
    y
    0.69
    an
    0.67
     can
    0.55
    one
    0.54
    ও
    0.50
    u
    0.49
    am
    0.47
    elike
    0.44
    ა
    0.44
    ia
    0.43
    Act Density 0.000%

    No Known Activations