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

    Neuronpedia

    INDEX
    Explanations

    Non-English language

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     corps
    -0.06
     haut
    -0.06
    叼
    -0.06
     chef
    -0.06
     uninsured
    -0.06
    䌀
    -0.06
    iner
    -0.06
     treeNode
    -0.06
    局
    -0.06
    usuario
    -0.06
    POSITIVE LOGITS
    ﺑ
    0.07
     sind
    0.07
    վ
    0.07
    עו
    0.07
     возмож
    0.07
    🈲
    0.07
    聞く
    0.07
    lan
    0.06
    UnityEngine
    0.06
    =X
    0.06
    Act Density 0.077%

    No Known Activations