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

    Neuronpedia

    INDEX
    Explanations

    News/Blog headlines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    239
    -0.07
     Dynamic
    -0.07
     cylindrical
    -0.07
     Delivery
    -0.06
    _out
    -0.06
     modeling
    -0.06
     kidneys
    -0.06
     XOR
    -0.06
     Nas
    -0.06
    iping
    -0.06
    POSITIVE LOGITS
    лем
    0.07
    urred
    0.06
    =#
    0.06
    keypress
    0.06
    ับความ
    0.06
    illac
    0.06
    [S
    0.06
    io
    0.06
    letic
    0.06
    ๋
    0.05
    Act Density 0.072%

    No Known Activations