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

    Neuronpedia

    INDEX
    Explanations

    HTML anchor links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Proof
    0.90
     proof
    0.89
    PROOF
    0.89
    Proof
    0.84
     handout
    0.77
     break
    0.77
     proofs
    0.76
    Explain
    0.73
    わたし
    0.73
     adju
    0.71
    POSITIVE LOGITS
    াক্তন
    0.84
    andı
    0.80
    াভাবিক
    0.79
    timedelta
    0.78
     შემთ
    0.76
    cargar
    0.75
     juegos
    0.75
    regator
    0.74
     tháng
    0.73
     MediaQuery
    0.72
    Act Density 0.000%

    No Known Activations