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

    Neuronpedia

    INDEX
    Explanations

    action

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    时时
    -0.07
    优点
    -0.07
     Habit
    -0.07
     dims
    -0.07
     etiquette
    -0.07
    _verified
    -0.07
     GG
    -0.07
     nick
    -0.07
    -tip
    -0.07
     Denied
    -0.07
    POSITIVE LOGITS
    сло
    0.08
    割
    0.08
    Partial
    0.07
     �
    0.07
     biochemical
    0.07
    ICI
    0.07
    ᴏ
    0.06
    0.06
     Sql
    0.06
    sequential
    0.06
    Act Density 0.001%

    No Known Activations