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

    Neuronpedia

    INDEX
    Explanations

    compensation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     aure
    -0.08
    LOUD
    -0.08
     tree
    -0.08
    _branch
    -0.07
    _root
    -0.07
     Science
    -0.07
     science
    -0.07
     Thu
    -0.07
    �数
    -0.07
     Books
    -0.07
    POSITIVE LOGITS
     compensation
    0.08
     Bennett
    0.07
     Compensation
    0.07
     compensate
    0.07
    ossip
    0.07
    bol
    0.07
     perc
    0.06
     compromise
    0.06
     counsel
    0.06
     Shepard
    0.06
    Act Density 0.005%

    No Known Activations