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

    Neuronpedia

    INDEX
    Explanations

    cultural/historical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    crollView
    -0.06
    (inflater
    -0.06
    #@
    -0.06
    aticon
    -0.06
    lossen
    -0.06
     habit
    -0.06
    협
    -0.06
    tabs
    -0.06
     晴
    -0.06
     acidic
    -0.06
    POSITIVE LOGITS
     stationed
    0.07
     trois
    0.07
     Infant
    0.06
     покол
    0.06
    .Button
    0.06
     reviewers
    0.06
    .hist
    0.06
     securing
    0.06
     payday
    0.06
    iculo
    0.06
    Act Density 0.001%

    No Known Activations