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

    Neuronpedia

    INDEX
    Explanations

    imagine, think, visualize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     thereby
    0.44
    似乎
    0.44
    总之
    0.43
     тобто
    0.43
     dabei
    0.42
    usual
    0.42
     devra
    0.42
     Nevertheless
    0.42
    であることが
    0.42
    Thus
    0.42
    POSITIVE LOGITS
     imagine
    2.08
     Imagine
    2.00
    Imagine
    1.93
    imagine
    1.85
    想象
    1.35
     imagines
    1.32
     think
    1.30
    想像
    1.26
     Think
    1.24
    想想
    1.24
    Act Density 0.016%

    No Known Activations