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

    Neuronpedia

    INDEX
    Explanations

    the or to

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     multiple
    -0.07
    'é
    -0.07
    -cart
    -0.06
     Bridges
    -0.06
     FILES
    -0.06
     chiếu
    -0.06
    ồm
    -0.06
     Una
    -0.06
     dictionaries
    -0.06
    idata
    -0.06
    POSITIVE LOGITS
    .blob
    0.06
    .navigationController
    0.06
     sized
    0.06
    949
    0.06
     anarch
    0.06
     Snape
    0.06
    .requests
    0.06
     chce
    0.06
     принимать
    0.06
    叔
    0.06
    Act Density 0.010%

    No Known Activations