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

    Neuronpedia

    INDEX
    Explanations

    scientific writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guys
    -0.07
    xoops
    -0.07
     все
    -0.06
     tenants
    -0.06
     ra
    -0.06
    妙
    -0.06
    .viewer
    -0.06
    ας
    -0.06
     ContentView
    -0.06
    租
    -0.06
    POSITIVE LOGITS
    handlers
    0.07
    adel
    0.07
    _CYCLE
    0.06
     minus
    0.06
     older
    0.06
    Neither
    0.06
    /NĐ
    0.06
    "text
    0.06
     žal
    0.06
     '/'↵
    0.06
    Act Density 0.137%

    No Known Activations