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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     більш
    -0.07
    Alex
    -0.07
     uveden
    -0.07
    Hum
    -0.07
     арх
    -0.06
    ูร
    -0.06
    _DETECT
    -0.06
    Facade
    -0.06
     аллерг
    -0.06
    학과
    -0.06
    POSITIVE LOGITS
     proceedings
    0.07
    POL
    0.06
     }));↵
    0.06
    Nation
    0.06
     fine
    0.06
     uncomfortable
    0.06
    -engine
    0.06
    bons
    0.06
    .Long
    0.06
    иж
    0.06
    Act Density 0.010%

    No Known Activations