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

    Neuronpedia

    INDEX
    Explanations

    character definitions and classes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     rufis
    0.49
     uniforms
    0.49
     renaming
    0.46
     ingrained
    0.46
     finances
    0.45
    isiä
    0.45
     inundated
    0.44
     emptied
    0.44
     societal
    0.43
     heartbreak
    0.43
    POSITIVE LOGITS
    骖
    0.47
    Wood
    0.46
     convincingly
    0.45
    Gui
    0.44
    Buy
    0.43
    旗下
    0.43
     приез
    0.43
     Put
    0.43
    urgiu
    0.42
     или
    0.42
    Act Density 0.001%

    No Known Activations