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

    Neuronpedia

    INDEX
    Explanations

    after effects after effects after effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    বে
    0.62
    ক
    0.60
     замі
    0.58
    ت
    0.58
    䚯
    0.56
    ون
    0.54
     переви
    0.54
    ر
    0.54
    ტ
    0.53
    IM
    0.52
    POSITIVE LOGITS
    人の
    0.54
     life
    0.49
    ની
    0.48
     people
    0.48
     untold
    0.48
     cosm
    0.47
     towering
    0.47
     prosperous
    0.46
     vita
    0.46
     quintessential
    0.46
    Act Density 0.004%

    No Known Activations