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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -Dec
    -0.06
    ones
    -0.06
     brokers
    -0.06
    overlap
    -0.06
    Writer
    -0.06
     Pocket
    -0.06
     <%
    -0.06
     показ
    -0.06
     Ryan
    -0.06
    Scanner
    -0.06
    POSITIVE LOGITS
    	initialize
    0.07
    _mass
    0.06
    _dynamic
    0.06
    .quest
    0.06
    україн
    0.06
    visibility
    0.06
    ISTER
    0.06
    /private
    0.06
    没有
    0.06
    _logits
    0.06
    Act Density 0.004%

    No Known Activations