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

    Neuronpedia

    INDEX
    Explanations

    emails short offer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Cave
    0.49
     Scripts
    0.45
     Задача
    0.44
    铮
    0.44
     mistakenly
    0.42
     Command
    0.40
     Jeśli
    0.40
     Legend
    0.39
     Im
    0.39
     Script
    0.39
    POSITIVE LOGITS
    countries
    0.50
    atletas
    0.47
    mektedir
    0.44
    𝟭
    0.44
    trifluoromethyl
    0.44
     येते
    0.43
    isEqualTo
    0.42
     한다
    0.42
     তুল
    0.41
    daftar
    0.41
    Act Density 0.004%

    No Known Activations