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

    Neuronpedia

    INDEX
    Explanations

    Current or future perception

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     standalone
    -0.07
    ClassName
    -0.07
    943
    -0.06
    .reward
    -0.06
     Find
    -0.06
     nrw
    -0.06
     defaultdict
    -0.06
     síd
    -0.06
    infeld
    -0.06
    飾
    -0.06
    POSITIVE LOGITS
     цього
    0.06
    Recording
    0.06
    $errors
    0.06
     incluso
    0.06
    sian
    0.06
    簡
    0.06
    GameManager
    0.06
    ：↵↵
    0.06
     filmm
    0.06
    ๐
    0.06
    Act Density 0.127%

    No Known Activations