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

    Neuronpedia

    INDEX
    Explanations

    claiming to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cu
    -0.06
    Them
    -0.06
     {/*
    -0.06
    .segment
    -0.06
    kraine
    -0.06
    riend
    -0.06
     shameful
    -0.06
    fires
    -0.06
     Fires
    -0.06
     政
    -0.06
    POSITIVE LOGITS
     summers
    0.07
     penned
    0.07
    繁
    0.07
     معل
    0.06
     getPlayer
    0.06
     defaults
    0.06
    早
    0.06
    可以
    0.06
     mdi
    0.06
     inser
    0.06
    Act Density 0.010%

    No Known Activations