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
     extending
    -0.07
     PROCUREMENT
    -0.07
    warehouse
    -0.06
     diseases
    -0.06
    sockets
    -0.06
    iqu
    -0.06
    ca
    -0.06
    eselect
    -0.06
    Li
    -0.06
    .wr
    -0.06
    POSITIVE LOGITS
     ditch
    0.07
    анов
    0.07
    amik
    0.06
    _twitter
    0.06
     IoT
    0.06
    搞
    0.06
     tehdy
    0.06
    	Element
    0.06
     impatient
    0.06
    =${
    0.06
    Act Density 0.027%

    No Known Activations