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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ili
    -0.07
     memberId
    -0.06
     Wild
    -0.06
     making
    -0.06
    .authorization
    -0.06
    were
    -0.06
    unicode
    -0.06
     make
    -0.06
     graphene
    -0.06
     production
    -0.06
    POSITIVE LOGITS
     It
    0.07
    [M
    0.07
    reece
    0.06
     They
    0.06
    [T
    0.06
    ็อต
    0.06
     lighting
    0.06
     Tato
    0.06
     zboží
    0.06
    _ENV
    0.06
    Act Density 0.092%

    No Known Activations