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

    Neuronpedia

    INDEX
    Explanations

    Rural

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     squirrel
    -0.07
     dirig
    -0.07
    .remaining
    -0.07
    redirect
    -0.07
    firstname
    -0.07
    .Feed
    -0.07
     fighter
    -0.07
    pii
    -0.06
    marine
    -0.06
    Story
    -0.06
    POSITIVE LOGITS
    ｯ
    0.07
     promised
    0.06
    {
↵
↵
    0.06
     elementary
    0.06
    Ѕ
    0.06
    示
    0.06
    ANCEL
    0.06
     GHC
    0.06
     everyday
    0.06
     duty
    0.05
    Act Density 0.001%

    No Known Activations