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

    Neuronpedia

    INDEX
    Explanations

    players

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hay
    -0.08
    comes
    -0.07
     ties
    -0.07
    졌
    -0.07
    츨
    -0.06
     ""));↵
    -0.06
    ttl
    -0.06
    unità
    -0.06
     solving
    -0.06
    aghetti
    -0.06
    POSITIVE LOGITS
    镍
    0.07
    弥漫
    0.07
    ㌶
    0.07
     lig
    0.07
    	Block
    0.07
    调配
    0.07
    哺乳
    0.07
    豆
    0.07
     Depot
    0.07
    都被
    0.07
    Act Density 0.015%

    No Known Activations