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

    Neuronpedia

    INDEX
    Explanations

    let's phrases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ในช่วง
    0.77
     Chỉ
    0.76
    ในการ
    0.72
    อย่างไร
    0.70
    द्री
    0.69
     locus
    0.69
    aS
    0.68
    ดังกล่าว
    0.67
     findest
    0.66
     sorts
    0.64
    POSITIVE LOGITS
     assume
    1.30
     pretend
    1.24
     preface
    1.18
     imagine
    1.15
     presume
    1.13
    assume
    1.06
    imagine
    1.02
    假設
    1.00
     suppose
    0.99
    Assume
    0.98
    Act Density 0.182%

    No Known Activations