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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    দিনই
    0.50
    勝ち
    0.49
    為主
    0.48
     slams
    0.47
     Gründe
    0.47
     injustices
    0.47
    ließen
    0.47
     critérios
    0.47
     mía
    0.46
     dní
    0.46
    POSITIVE LOGITS
     Imagery
    0.48
     Тре
    0.46
    0
    0.46
    9
    0.46
     Magical
    0.45
     Cozy
    0.44
    Imagery
    0.44
    Ин
    0.44
     Clever
    0.43
     Genetics
    0.43
    Act Density 0.000%

    No Known Activations