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

    Neuronpedia

    INDEX
    Explanations

    dom

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    overlay
    -0.07
     VLAN
    -0.07
    PackageManager
    -0.06
    _Ph
    -0.06
    ưu
    -0.06
    loff
    -0.06
     Harvest
    -0.06
     nakne
    -0.06
    都会
    -0.06
     Weiner
    -0.06
    POSITIVE LOGITS
    бы
    0.07
    rips
    0.07
    regulated
    0.07
     mě
    0.06
     OM
    0.06
    	MD
    0.06
     dispose
    0.06
     EOS
    0.06
     snapshots
    0.06
    >
    0.06
    Act Density 0.006%

    No Known Activations