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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     breast
    -0.06
    goal
    -0.06
     lunch
    -0.06
     söyley
    -0.06
    �
    -0.06
     одерж
    -0.06
     MON
    -0.05
     Fla
    -0.05
    .Ge
    -0.05
    igator
    -0.05
    POSITIVE LOGITS
    ’ét
    0.07
    )],
    0.07
     оттен
    0.07
    JECTED
    0.07
    ตรง
    0.06
    Clients
    0.06
    .Ver
    0.06
    reno
    0.06
     خیلی
    0.06
    ถาม
    0.06
    Act Density 2.968%

    No Known Activations