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

    Neuronpedia

    INDEX
    Explanations

    terms related to fashion, craftsmanship, or scientific recognition

    oai_token-act-pair · gemini-2.0-flash

    Fashion, medicine, science

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AddTagHelper
    -0.65
    AutoScale
    -0.59
    ыгана
    -0.54
    expandindo
    -0.54
    脚注の使い方
    -0.53
     Roskov
    -0.53
     rechange
    -0.50
     виправивши
    -0.50
    ssohn
    -0.49
    IContainer
    -0.48
    POSITIVE LOGITS
     שוליים
    0.60
     EconPapers
    0.56
    reinterpret
    0.52
    principalColumn
    0.52
     knowledge
    0.51
     ujednoznacz
    0.51
     sense
    0.51
     critic
    0.51
     community
    0.50
    incl
    0.50
    Act Density 2.257%

    No Known Activations