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

    Neuronpedia

    INDEX
    Explanations

    Inc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blízk
    -0.07
     σε
    -0.07
    Cache
    -0.06
    -Muslim
    -0.06
    _rm
    -0.06
    .sendKeys
    -0.06
    lış
    -0.06
    preci
    -0.06
     Retry
    -0.06
    IGENCE
    -0.06
    POSITIVE LOGITS
     lieutenant
    0.07
    fruit
    0.06
    ой
    0.06
    (employee
    0.06
    .WriteLine
    0.06
    .src
    0.06
     sentiment
    0.06
     Eu
    0.06
     Francisco
    0.06
    Bag
    0.06
    Act Density 0.001%

    No Known Activations