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

    Neuronpedia

    INDEX
    Explanations

    follow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    esen
    -0.07
    Nullable
    -0.07
    Die
    -0.07
    ImageContext
    -0.07
    "><
    -0.07
     Henry
    -0.06
    ).↵↵
    -0.06
    )↵↵
    -0.06
     halde
    -0.06
    ováním
    -0.06
    POSITIVE LOGITS
     blinded
    0.07
    _CNTL
    0.07
     SAFE
    0.07
    _bulk
    0.06
    USART
    0.06
    英国
    0.06
     영국
    0.06
    .payment
    0.06
    	pr
    0.06
    矢
    0.06
    Act Density 0.000%

    No Known Activations