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

    Neuronpedia

    INDEX
    Explanations

    speech or reports by authority figures

    oai_token-act-pair · gemini-2.0-flash

    said/that

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    "])
    -0.55
    eren
    -0.50
    '])->
    -0.46
    ++
    -0.44
    анна
    -0.44
     говори
    -0.44
    OrBuilder
    -0.42
     })
    -0.41
    xase
    -0.41
    Shots
    -0.41
    POSITIVE LOGITS
     AssemblyProduct
    0.87
     AssemblyTitle
    0.75
    TestingModule
    0.70
    fromnode
    0.66
    invokeLater
    0.62
    AndEndTag
    0.61
     ujednoznacz
    0.61
    XmlIgnore
    0.60
    usermodel
    0.60
     despite
    0.59
    Act Density 1.010%

    No Known Activations