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

    Neuronpedia

    INDEX
    Explanations

    Joseph

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     runaway
    -0.06
    	ff
    -0.06
     хол
    -0.06
    529
    -0.06
     swath
    -0.06
    _strip
    -0.06
    629
    -0.06
     Γκ
    -0.06
    _SQL
    -0.06
    unread
    -0.06
    POSITIVE LOGITS
     Joseph
    0.11
     José
    0.10
     Joe
    0.09
     Josef
    0.09
    Joseph
    0.09
    placed
    0.09
     Maria
    0.08
    eresa
    0.08
    assi
    0.08
     Jose
    0.07
    Act Density 0.012%

    No Known Activations