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

    Neuronpedia

    INDEX
    Explanations

    never or forever states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     During
    0.48
     টানা
    0.47
     unsurprisingly
    0.47
     during
    0.45
     busy
    0.45
     eager
    0.44
     underway
    0.44
     spun
    0.43
     Delay
    0.43
     Phot
    0.42
    POSITIVE LOGITS
     forever
    1.05
    永远
    0.99
    forever
    0.98
     jamás
    0.96
    一生
    0.88
    Nunca
    0.88
    never
    0.87
    永遠
    0.87
     никогда
    0.86
     lifetime
    0.85
    Act Density 0.053%

    No Known Activations