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

    Neuronpedia

    INDEX
    Explanations

    foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Omega
    -0.06
    ):\
    -0.06
    /example
    -0.05
    (which
    -0.05
     Recover
    -0.05
    /connect
    -0.05
     disjoint
    -0.05
     Message
    -0.05
     diz
    -0.05
     mes
    -0.05
    POSITIVE LOGITS
    aciones
    0.07
    ución
    0.07
    ++.
    0.07
     Exploration
    0.07
    .ExecuteReader
    0.07
    ダ
    0.07
     إن
    0.07
     trendy
    0.07
    maint
    0.06
     général
    0.06
    Act Density 0.022%

    No Known Activations