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

    Neuronpedia

    INDEX
    Explanations

    your

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Looks
    -0.08
    觊
    -0.07
    看着
    -0.07
     gorge
    -0.07
    ً
    -0.07
    擅
    -0.07
    ltre
    -0.07
    엶
    -0.07
    looking
    -0.06
    ić
    -0.06
    POSITIVE LOGITS
     legalized
    0.08
     Beef
    0.08
     compounded
    0.07
    青铜
    0.07
    팻
    0.07
     ба
    0.07
    ('?
    0.06
    ********************************************************************************
    0.06
    //*
    0.06
     bystand
    0.06
    Act Density 0.023%

    No Known Activations