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

    Neuronpedia

    INDEX
    Explanations

    references to years and political figures

    oai_token-act-pair · gemini-2.0-flash

    non-English tokens or code-related terms

    np_token-act-pair-logits · gpt-4o-mini

    0

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    +#+
    -0.65
     '\\;'
    -0.62
    — 
    -0.59
    DataAnnotations
    -0.57
    DockStyle
    -0.55
     LSA
    -0.55
    PhysRevD
    -0.54
    ledem
    -0.53
    EnableWeb
    -0.53
    脚注の使い方
    -0.52
    POSITIVE LOGITS
    béco
    0.57
     Biôgrafia
    0.51
    findpost
    0.51
    зульта
    0.49
    ekse
    0.49
    StrictEqual
    0.47
    cookieParser
    0.47
     precisione
    0.46
    protoimpl
    0.45
     titoli
    0.45
    Act Density 0.578%

    No Known Activations