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

    Neuronpedia

    INDEX
    Explanations

    Spring annotations and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ギュア
    0.47
     bean
    0.44
     thisTrack
    0.44
     couche
    0.43
    芓
    0.43
     beans
    0.43
    扫描
    0.42
     উত্তরাধ
    0.42
    类
    0.41
    Bean
    0.41
    POSITIVE LOGITS
    representing
    0.50
     representing
    0.46
    els
    0.40
     So
    0.39
    upt
    0.38
    iosa
    0.38
    proven
    0.38
    used
    0.38
    introduced
    0.36
    organized
    0.36
    Act Density 0.000%

    No Known Activations