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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uttle
    -0.07
     drink
    -0.07
    odafone
    -0.07
    ats
    -0.06
     detectives
    -0.06
     owning
    -0.06
     CW
    -0.06
    рож
    -0.06
    draulic
    -0.06
    виг
    -0.06
    POSITIVE LOGITS
     forb
    0.07
    greater
    0.06
     воду
    0.06
     whichever
    0.06
    ([$
    0.06
    Conv
    0.06
    .rad
    0.06
     Py
    0.06
     форму
    0.06
     \"$
    0.06
    Act Density 0.037%

    No Known Activations