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

    Neuronpedia

    INDEX
    Explanations

    race

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mutating
    -0.06
     bites
    -0.06
    登録
    -0.06
    นๆ
    -0.06
     }),↵
    -0.06
     fills
    -0.06
     TEST
    -0.06
     Sco
    -0.06
    	reload
    -0.06
     youre
    -0.06
    POSITIVE LOGITS
     Political
    0.08
    nuts
    0.07
    (File
    0.07
    ेकर
    0.06
    odon
    0.06
     political
    0.06
    led
    0.06
    rott
    0.06
     chopped
    0.06
     dehydration
    0.06
    Act Density 0.000%

    No Known Activations