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

    Neuronpedia

    INDEX
    Explanations

    variations of the word "new."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    new year or account

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ſta
    -0.52
     pleaſure
    -0.43
     Majefty
    -0.42
    StoryboardSegue
    -0.41
     useStyles
    -0.40
    ailles
    -0.40
    licante
    -0.39
     ſmall
    -0.38
     purpoſe
    -0.38
     bords
    -0.37
    POSITIVE LOGITS
     New
    1.13
    New
    1.08
     NEW
    0.72
    在新
    0.71
    新
    0.71
    new
    0.68
     Новый
    0.68
     Nuevas
    0.68
    NEW
    0.67
    rungsseite
    0.67
    Act Density 0.007%

    No Known Activations