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

    Neuronpedia

    INDEX
    Explanations

    publication

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Rahman
    -0.07
     Boutique
    -0.06
    φων
    -0.06
    orges
    -0.06
     Disabled
    -0.06
     Thames
    -0.06
    시간
    -0.06
     VR
    -0.06
     mapView
    -0.06
    iqué
    -0.06
    POSITIVE LOGITS
    ��
    0.06
     anlamda
    0.06
     наб
    0.06
    anth
    0.06
    pic
    0.06
    =q
    0.06
     Gorgeous
    0.06
    =http
    0.06
     #
↵
    0.06
    砂
    0.06
    Act Density 0.002%

    No Known Activations