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

    Neuronpedia

    INDEX
    Explanations

    continuous

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slapped
    -0.07
     sacr
    -0.07
     slogans
    -0.07
     rank
    -0.07
     spanking
    -0.06
     shattered
    -0.06
     weak
    -0.06
     legs
    -0.06
     knight
    -0.06
     figure
    -0.06
    POSITIVE LOGITS
     Continuous
    0.10
     continuous
    0.10
     continuously
    0.08
     continually
    0.08
     continue
    0.08
    continued
    0.08
     continued
    0.07
    }")
    0.07
    orderId
    0.07
     Montreal
    0.07
    Act Density 0.042%

    No Known Activations