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

    Neuronpedia

    INDEX
    Explanations

    items described with adjectives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    тре
    0.54
     milhões
    0.52
     аны
    0.48
    ру
    0.47
    }$
    0.47
    рен
    0.46
    лен
    0.45
    猀
    0.45
     obligado
    0.45
    тическая
    0.44
    POSITIVE LOGITS
    four
    0.53
     eatery
    0.49
    pointing
    0.48
    goal
    0.47
    inthe
    0.46
    ‼
    0.45
    sp
    0.45
    ARM
    0.45
    fight
    0.44
    Synchron
    0.44
    Act Density 0.001%

    No Known Activations