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

    Neuronpedia

    INDEX
    Explanations

    persons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ByName
    -0.08
     some
    -0.07
     EIF
    -0.07
    lider
    -0.07
     Wilhelm
    -0.06
     Chargers
    -0.06
     نامه
    -0.06
    onom
    -0.06
    lossen
    -0.06
    جموع
    -0.06
    POSITIVE LOGITS
    _LS
    0.06
    >');
↵
    0.06
     borrowers
    0.06
    \Persistence
    0.06
     sweat
    0.06
    ?",
    0.06
    _rec
    0.06
    Overlay
    0.06
     dne
    0.06
    션
    0.06
    Act Density 0.001%

    No Known Activations