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

    Neuronpedia

    INDEX
    Explanations

    cap

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    named
    -0.07
    blers
    -0.07
    delivr
    -0.07
    陆
    -0.06
    .getStatus
    -0.06
    �
    -0.06
    "g
    -0.06
     bytes
    -0.06
     inflated
    -0.06
     (${
    -0.06
    POSITIVE LOGITS
     meets
    0.08
     ascertain
    0.07
     evitar
    0.07
     prv
    0.06
     पह
    0.06
     resist
    0.06
     پاک
    0.06
     gaining
    0.06
     menn
    0.06
     Москва
    0.06
    Act Density 0.005%

    No Known Activations