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

    Neuronpedia

    INDEX
    Explanations

    Forum posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _btn
    -0.06
    _path
    -0.06
     hostile
    -0.06
     modo
    -0.06
    (dir
    -0.06
    oshi
    -0.06
     dou
    -0.06
     cố
    -0.06
     reuse
    -0.06
    Into
    -0.06
    POSITIVE LOGITS
    \↵
    0.08
     komment
    0.06
     ideally
    0.06
    \
↵
    0.06
     |
↵
    0.06
    *K
    0.06
    discord
    0.06
     &(
    0.06
    ""↵
    0.06
     ґ
    0.06
    Act Density 0.079%

    No Known Activations