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

    Neuronpedia

    INDEX
    Explanations

    substrings of letters and numbers representing identifiers, likely from code

    oai_token-act-pair · gemini-2.0-flash

    Code, numbers, references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     }{@
    -0.70
    .))
    -0.60
    IntoConstraints
    -0.58
    AccessorTable
    -0.57
     nämlich
    -0.56
    :✨
    -0.55
    .'”
    -0.54
     resourceCulture
    -0.53
     TestBed
    -0.52
    )])
    -0.51
    POSITIVE LOGITS
     TAMBÉM
    0.54
    Население
    0.53
     protoimpl
    0.52
     bekasi
    0.52
    География
    0.52
     IUCN
    0.51
     चीज़ों
    0.51
    actionMode
    0.50
     pstmt
    0.50
    Портал
    0.49
    Act Density 0.435%

    No Known Activations