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

    Neuronpedia

    INDEX
    Explanations

    has

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gre
    -0.07
    clist
    -0.07
     space
    -0.07
     dri
    -0.07
     figure
    -0.07
     flames
    -0.07
    火
    -0.07
    脑
    -0.07
    引力
    -0.06
     Fr
    -0.06
    POSITIVE LOGITS
     locationManager
    0.07
    얻
    0.07
    还会
    0.07
    .="<
    0.07
    รายงาน
    0.07
     diversified
    0.07
    -shell
    0.07
    []=$
    0.07
    addItem
    0.07
    ('//
    0.07
    Act Density 0.003%

    No Known Activations