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

    Neuronpedia

    INDEX
    Explanations

    continuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     señor
    -0.08
    /preferences
    -0.07
    かもしれませんが
    -0.07
    _restart
    -0.07
     NPCs
    -0.07
     Mare
    -0.07
    我对
    -0.07
     -->
↵
↵
    -0.07
    xeb
    -0.07
    血脉
    -0.07
    POSITIVE LOGITS
     Goals
    0.08
    挂号
    0.08
     goal
    0.08
     goals
    0.07
     innovative
    0.07
    槱
    0.07
    Bounding
    0.07
    扩建
    0.07
    ᤖ
    0.07
    �
    0.07
    Act Density 0.009%

    No Known Activations