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

    Neuronpedia

    INDEX
    Explanations

    locations and sections

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     summ
    -0.07
    %"><
    -0.06
    риз
    -0.06
     rejo
    -0.06
     Prov
    -0.06
    	priv
    -0.06
     Purs
    -0.06
     Stable
    -0.06
    iji
    -0.06
    ("~
    -0.06
    POSITIVE LOGITS
    .Contact
    0.06
     Grave
    0.06
    职业
    0.06
    .xls
    0.06
     району
    0.06
     Detected
    0.06
    などの
    0.06
     Bristol
    0.06
    чис
    0.06
     startIndex
    0.06
    Act Density 0.156%

    No Known Activations