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

    Neuronpedia

    INDEX
    Explanations

    dialogue interjections and affirmations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ,
    0.92
    ،
    0.85
    、
    0.83
    .--
    0.81
    Также
    0.79
    Ainsi
    0.77
    ,…
    0.76
     Также
    0.76
    ,--
    0.75
    Additionally
    0.75
    POSITIVE LOGITS
     yeah
    1.33
     huh
    1.18
     eh
    1.05
     but
    1.03
     yep
    1.01
     alright
    1.01
     okay
    1.00
     yes
    1.00
     haha
    0.98
     aye
    0.95
    Act Density 0.608%

    No Known Activations