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

    Neuronpedia

    INDEX
    Explanations

    #define

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    evice
    -0.08
    .ids
    -0.08
     آلاف
    -0.07
    佶
    -0.07
    aco
    -0.07
     Projectile
    -0.07
     blanco
    -0.07
     mogul
    -0.07
     PDO
    -0.06
    socket
    -0.06
    POSITIVE LOGITS
    믜
    0.08
     Nov
    0.07
     testimony
    0.07
    иров
    0.07
     المح
    0.07
    ])));↵
    0.07
    .water
    0.07
    とにかく
    0.07
    المع
    0.07
    leground
    0.07
    Act Density 0.001%

    No Known Activations