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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .swing
    -0.06
    .Printf
    -0.06
    �
    -0.06
    -American
    -0.06
    )index
    -0.06
     Vk
    -0.06
     박
    -0.06
    _Construct
    -0.06
    цвет
    -0.06
    /script
    -0.06
    POSITIVE LOGITS
     abroad
    0.07
     wakeup
    0.06
     guaranteed
    0.06
    reflection
    0.06
     antiqu
    0.06
     apartments
    0.06
     Sunderland
    0.06
    estion
    0.06
     announces
    0.06
     ż
    0.06
    Act Density 0.025%

    No Known Activations