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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .MATCH
    -0.07
    .Owner
    -0.06
    );;↵
    -0.06
    jwt
    -0.06
    ()!=
    -0.06
    ("'
    -0.06
     salt
    -0.06
    dbe
    -0.06
     Ish
    -0.06
     MAV
    -0.06
    POSITIVE LOGITS
    free
    0.07
     gái
    0.07
    ρισ
    0.07
     карт
    0.06
     Dem
    0.06
     περισσότε
    0.06
    gray
    0.06
    ρε
    0.06
     پیشینه
    0.06
     hoạch
    0.06
    Act Density 0.003%

    No Known Activations