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

    Neuronpedia

    INDEX
    Explanations

    Numerical ranges and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xsd
    -0.07
     daunting
    -0.07
    "What
    -0.07
    Slave
    -0.07
    “What
    -0.07
    .Service
    -0.07
     Niagara
    -0.07
    "Oh
    -0.07
     amazing
    -0.06
     Dining
    -0.06
    POSITIVE LOGITS
     тор
    0.06
     zásad
    0.06
    connections
    0.06
    ingo
    0.06
    HG
    0.06
    _coupon
    0.06
     �
    0.06
     AppConfig
    0.06
     VA
    0.06
    classNames
    0.06
    Act Density 0.005%

    No Known Activations