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

    Neuronpedia

    INDEX
    Explanations

    Ana

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    될
    -0.07
    $I
    -0.07
     vested
    -0.06
    ocoder
    -0.06
     Hil
    -0.06
     Julius
    -0.06
     gravel
    -0.06
    ifier
    -0.06
     Mitt
    -0.06
     underst
    -0.06
    POSITIVE LOGITS
     ana
    0.08
     Anaheim
    0.07
    .pow
    0.07
    .cgColor
    0.07
    !=↵
    0.07
    asic
    0.07
    >'+↵
    0.06
    EXPECT
    0.06
    Ana
    0.06
    ");
↵
    0.06
    Act Density 0.004%

    No Known Activations