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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    whereIn
    -0.08
     interpreting
    -0.08
    相对来说
    -0.07
    _unregister
    -0.07
    infer
    -0.07
     {/*
    -0.07
     REQ
    -0.07
     contraceptive
    -0.07
    _Up
    -0.07
    (box
    -0.07
    POSITIVE LOGITS
     قال
    0.07
     Closing
    0.06
     tty
    0.06
     Cobb
    0.06
    莫斯科
    0.06
    五
    0.06
    -agent
    0.06
    .static
    0.06
     Mayo
    0.06
    	offset
    0.06
    Act Density 0.051%

    No Known Activations