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

    Neuronpedia

    INDEX
    Explanations

    hi / hello greetings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ########.
    -0.09
     ï¼¼:
    -0.09
    allet
    -0.09
    ëģĶ
    -0.09
    ì©
    -0.09
     vlas
    -0.09
    仪
    -0.09
    _firstname
    -0.09
    ôt
    -0.08
     Boulevard
    -0.08
    POSITIVE LOGITS
     Hi
    0.18
    Hi
    0.16
    Hello
    0.15
    hi
    0.14
     hi
    0.14
     HI
    0.13
     Hello
    0.13
    HI
    0.12
     hello
    0.11
    _hi
    0.11
    Act Density 0.097%

    No Known Activations