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

    Neuronpedia

    INDEX
    Explanations

    database queries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .events
    -0.07
     producers
    -0.06
    療
    -0.06
     اض
    -0.06
    _visibility
    -0.06
    handler
    -0.06
     υπάρχουν
    -0.06
    obbies
    -0.06
     pool
    -0.06
     Zion
    -0.06
    POSITIVE LOGITS
     вважа
    0.07
     مواطنة
    0.07
     VIR
    0.06
     sono
    0.06
     orang
    0.06
     заболевания
    0.06
     }
↵
↵
↵
    0.06
     форма
    0.06
    until
    0.06
     celib
    0.06
    Act Density 0.026%

    No Known Activations