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

    Neuronpedia

    INDEX
    Explanations

    sexual situations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reshape
    -0.06
    波
    -0.06
    Pictures
    -0.06
    (character
    -0.06
    ASHINGTON
    -0.06
    ramids
    -0.06
     flexibility
    -0.06
     Nat
    -0.06
     toppings
    -0.06
     distances
    -0.06
    POSITIVE LOGITS
    skb
    0.07
     (
↵
    0.06
    emic
    0.06
    olph
    0.06
    คณะ
    0.06
    	ff
    0.06
    (flag
    0.06
    imates
    0.06
     refuse
    0.06
     губер
    0.06
    Act Density 0.051%

    No Known Activations