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

    Neuronpedia

    INDEX
    Explanations

    prejudice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    亚洲
    -0.06
     sofort
    -0.06
     Suppress
    -0.06
    ський
    -0.06
     poplat
    -0.06
    Bins
    -0.06
     itemList
    -0.06
    山市
    -0.06
     mView
    -0.06
     compass
    -0.06
    POSITIVE LOGITS
     LES
    0.07
     freelance
    0.06
    摘
    0.06
     Power
    0.06
     power
    0.06
    >[]
    0.06
     المك
    0.06
    Through
    0.06
     packing
    0.06
     Aut
    0.06
    Act Density 0.000%

    No Known Activations