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

    Neuronpedia

    INDEX
    Explanations

    auxiliary verb + predicate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ব
    1.68
    हाल
    1.62
    aust
    1.60
    ◦
    1.59
    Tenant
    1.59
    いき
    1.57
    কারীর
    1.56
    นี้
    1.56
    SU
    1.54
    elő
    1.53
    POSITIVE LOGITS
     indeed
    1.96
    ية
    1.91
    ği
    1.84
    时候
    1.70
    ity
    1.63
    あります
    1.61
     возника
    1.60
    蕤
    1.59
    否
    1.57
    出産
    1.57
    Act Density 0.263%

    No Known Activations