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

    Neuronpedia

    INDEX
    Explanations

    similes using "like a"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    显然
    0.87
    Apparently
    0.85
     presumably
    0.82
    presumably
    0.82
    を用いる
    0.76
    Regardless
    0.75
     tentu
    0.74
     następnie
    0.73
     Apparently
    0.73
     reportedly
    0.72
    POSITIVE LOGITS
     Lego
    1.13
     sandpaper
    1.12
     molasses
    1.08
     lego
    1.05
     velcro
    1.03
     dynamite
    1.01
     Velcro
    0.98
     wallpaper
    0.98
     LEGO
    0.96
     Cinderella
    0.94
    Act Density 0.458%

    No Known Activations