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

    Neuronpedia

    INDEX
    Explanations

    building organizations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -quarter
    -0.07
     visit
    -0.07
    iece
    -0.06
    Psi
    -0.06
     interpersonal
    -0.06
    _sell
    -0.06
     stones
    -0.06
     من
    -0.06
     Persian
    -0.06
     Japanese
    -0.06
    POSITIVE LOGITS
    
    0.07
    IMIZE
    0.07
    (obj
    0.06
    />.↵
    0.06
    \"]
    0.06
    нима
    0.06
     {

↵
    0.06
    (ConfigurationManager
    0.06
    「……
    0.06
    ั่
    0.06
    Act Density 0.020%

    No Known Activations