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

    Neuronpedia

    INDEX
    Explanations

    of the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     resident
    -0.07
    IFICATE
    -0.06
     jong
    -0.06
     messages
    -0.06
     icon
    -0.06
     District
    -0.06
     نشده
    -0.06
    _EXCEPTION
    -0.06
     Laure
    -0.06
     territor
    -0.06
    POSITIVE LOGITS
     Sterling
    0.07
    ποίηση
    0.07
    ờ
    0.07
    ↵			↵
    0.06
    embre
    0.06
     opc
    0.06
    /'↵↵
    0.06
    цеп
    0.06
     Rogue
    0.06
     SZ
    0.06
    Act Density 0.014%

    No Known Activations