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

    Neuronpedia

    INDEX
    Explanations

    assumption or supposition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     itemId
    0.39
    ROM
    0.39
     করিয়াছিল
    0.38
     scraper
    0.38
     hadc
    0.38
    ल्हे
    0.38
    ląd
    0.37
    ございました
    0.37
     लैपटॉप
    0.37
    ğmen
    0.37
    POSITIVE LOGITS
     Assume
    0.71
    Assume
    0.67
     assume
    0.66
     Assuming
    0.65
    Assuming
    0.61
     assuming
    0.60
     Suppose
    0.60
    assume
    0.60
    假设
    0.59
     nobody
    0.57
    Act Density 0.012%

    No Known Activations