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

    Neuronpedia

    INDEX
    Explanations

    as [modifier] as

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     imagine
    0.60
     Imagine
    0.55
    imagine
    0.53
    Imagine
    0.52
     imagining
    0.50
    想像
    0.50
     imagines
    0.49
     імені
    0.49
     Imag
    0.43
    想象
    0.43
    POSITIVE LOGITS
     as
    0.94
     както
    0.55
     যতটা
    0.55
    as
    0.54
     όσο
    0.52
     sebag
    0.49
     than
    0.48
    为例
    0.48
     као
    0.48
     quanto
    0.47
    Act Density 0.012%

    No Known Activations