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

    Neuronpedia

    INDEX
    Explanations

    organizations and systems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .startswith
    -0.08
     Е
    -0.07
    ocs
    -0.07
     rural
    -0.07
    )i
    -0.07
     мас
    -0.06
    _hello
    -0.06
    olor
    -0.06
     مش
    -0.06
    .Repository
    -0.06
    POSITIVE LOGITS
    SIGN
    0.06
     readability
    0.06
    LV
    0.06
     cria
    0.06
    661
    0.06
     jewelry
    0.06
     backups
    0.06
     yytype
    0.06
    Void
    0.06
    RU
    0.06
    Act Density 0.299%

    No Known Activations