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

    Neuronpedia

    INDEX
    Explanations

    considering investing, cover deficits, cat owners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sustaining
    0.52
     تقویت
    0.49
    牧
    0.47
    軗
    0.47
    custList
    0.46
    ﺿ
    0.46
    쐞
    0.45
    Hepin
    0.44
    楽
    0.44
    continuity
    0.44
    POSITIVE LOGITS
     bure
    0.50
     Kag
    0.49
     he
    0.46
     nap
    0.46
     kab
    0.46
    olog
    0.45
    er
    0.45
     agarr
    0.45
    0.45
    en
    0.44
    Act Density 0.002%

    No Known Activations