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

    Neuronpedia

    INDEX
    Explanations

    code/data structures

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VAL
    -0.07
    ніх
    -0.06
    Dia
    -0.06
     holster
    -0.06
     cen
    -0.06
    TK
    -0.06
     plummet
    -0.06
    portrait
    -0.06
    _dual
    -0.06
     aliases
    -0.06
    POSITIVE LOGITS
     інозем
    0.07
    	↵		↵
    0.07
    ↵
↵
↵
    0.07
     unnecessarily
    0.06
    }
↵
↵
↵
    0.06
    UL
    0.06
     searchBar
    0.06
    .interfaces
    0.06
    خو
    0.06
    ....↵↵
    0.06
    Act Density 0.001%

    No Known Activations