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

    Neuronpedia

    INDEX
    Explanations

    Chinese/Japanese inspection terms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Btn
    -0.07
    554
    -0.07
    mv
    -0.06
     thumb
    -0.06
     delta
    -0.06
     plus
    -0.06
    .Linear
    -0.06
     Plus
    -0.06
    976
    -0.06
     tragedy
    -0.06
    POSITIVE LOGITS
     wb
    0.07
    grant
    0.06
    .MON
    0.06
    -exclusive
    0.06
    �
    0.06
    SHOP
    0.06
    iesz
    0.06
    養
    0.06
    روش
    0.06
    Prior
    0.06
    Act Density 0.037%

    No Known Activations