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

    Neuronpedia

    INDEX
    Explanations

    special topics or contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ਜਾਣ
    0.40
    ज्ञापन
    0.39
    tax
    0.36
     ジャ
    0.36
    width
    0.35
    逦
    0.35
    Freight
    0.34
     influencers
    0.34
    Jy
    0.33
     jails
    0.33
    POSITIVE LOGITS
     frontend
    0.39
     brittle
    0.38
    疏
    0.38
    onese
    0.38
     baptism
    0.38
    っぱい
    0.38
     programming
    0.37
     VEGF
    0.37
    elli
    0.37
     વિશે
    0.36
    Act Density 0.002%

    No Known Activations