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

    Neuronpedia

    INDEX
    Explanations

    personal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Robin
    -0.07
    _lista
    -0.07
    Repo
    -0.06
     KK
    -0.06
    .city
    -0.06
     Fro
    -0.06
    -proof
    -0.06
    .member
    -0.06
    _real
    -0.06
     Brooke
    -0.06
    POSITIVE LOGITS
    (expr
    0.07
    ucket
    0.07
     datingside
    0.07
    alesce
    0.06
     targeting
    0.06
    viously
    0.06
    �다
    0.06
    _Api
    0.06
    cling
    0.06
     Overlay
    0.06
    Act Density 0.016%

    No Known Activations