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

    Neuronpedia

    INDEX
    Explanations

    news reports

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    官网
    -0.08
    Ин
    -0.07
     Perspectives
    -0.06
    Seed
    -0.06
    Cro
    -0.06
    싱
    -0.06
    _schema
    -0.06
     psychiatrist
    -0.06
     нее
    -0.06
     Is
    -0.06
    POSITIVE LOGITS
    iques
    0.07
     transparent
    0.07
    KeyPress
    0.07
     cambios
    0.06
     vš
    0.06
     etmiş
    0.06
     |
↵
    0.06
     commissions
    0.06
     found
    0.06
    
    0.06
    Act Density 0.016%

    No Known Activations