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

    Neuronpedia

    INDEX
    Explanations

    receiving

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     другим
    -0.07
    (Camera
    -0.06
    klass
    -0.06
     roli
    -0.06
     Θε
    -0.06
     revolution
    -0.06
    (fun
    -0.06
     metropolitan
    -0.06
     BANK
    -0.06
    travel
    -0.06
    POSITIVE LOGITS
     blouse
    0.08
        
↵
↵
    0.06
    ually
    0.06
    _pd
    0.06
     vape
    0.06
    719
    0.06
    基金
    0.06
     elementType
    0.06
    zept
    0.06
     Swinger
    0.06
    Act Density 0.001%

    No Known Activations