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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     //"
    -0.06
    ControlItem
    -0.06
    OLE
    -0.06
     conquered
    -0.06
     immigrant
    -0.06
    ２０
    -0.06
     coefficient
    -0.06
    -Fi
    -0.06
     EXPER
    -0.06
    (Profile
    -0.06
    POSITIVE LOGITS
    ClassNotFoundException
    0.07
     khách
    0.07
     separating
    0.07
     remain
    0.07
     contacting
    0.06
    이지
    0.06
    มาย
    0.06
    abort
    0.06
    _starts
    0.06
     dobu
    0.06
    Act Density 0.049%

    No Known Activations