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

    Neuronpedia

    INDEX
    Explanations

    achieve key milestones

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    媾
    0.41
     fara
    0.41
     labour
    0.39
    aları
    0.39
     Fla
    0.39
     entrusted
    0.39
     trusts
    0.38
     dictator
    0.38
     उर्व
    0.38
    儼
    0.38
    POSITIVE LOGITS
     story
    0.51
     STORY
    0.49
    story
    0.48
     داستان
    0.47
    Neal
    0.46
    Story
    0.46
    ストーリー
    0.46
     chuyện
    0.46
     واقع
    0.45
     গল্পের
    0.45
    Act Density 0.000%

    No Known Activations