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

    Neuronpedia

    INDEX
    Explanations

    say "distributed"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    emption
    -0.06
    Пр
    -0.06
    .*/↵
    -0.06
     dinero
    -0.06
     Skyl
    -0.06
    ('/')[
    -0.06
    她的
    -0.06
    })
↵
    -0.06
    letion
    -0.06
     Buccaneers
    -0.06
    POSITIVE LOGITS
    äsent
    0.08
     dinners
    0.07
     xung
    0.06
    contained
    0.06
    .fn
    0.06
     RuntimeMethod
    0.06
     deposition
    0.06
     влаж
    0.06
    _mr
    0.06
     ofType
    0.06
    Act Density 0.005%

    No Known Activations