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

    Neuronpedia

    INDEX
    Explanations

    .begin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Ac
    -0.07
     Robbins
    -0.07
    Resource
    -0.07
     mistress
    -0.06
    :M
    -0.06
    them
    -0.06
     Parl
    -0.06
     admire
    -0.06
     Manor
    -0.06
     Palmer
    -0.06
    POSITIVE LOGITS
     Jonah
    0.06
     tick
    0.06
    	↵↵↵
    0.06
     ={↵
    0.06
     предвар
    0.06
     FedEx
    0.06
    하는데
    0.06
    textField
    0.06
     mange
    0.06
     sincerely
    0.06
    Act Density 0.001%

    No Known Activations