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

    Neuronpedia

    INDEX
    Explanations

    agency

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     towers
    -0.07
    _SHADOW
    -0.07
    اطعة
    -0.06
    izioni
    -0.06
     هزار
    -0.06
    icial
    -0.06
     tower
    -0.06
     aligned
    -0.06
    ений
    -0.06
    osed
    -0.06
    POSITIVE LOGITS
     agent
    0.09
     agents
    0.08
     Agents
    0.08
     agency
    0.08
     agencies
    0.07
    Empresa
    0.07
     Agency
    0.07
     Agent
    0.07
    >G
    0.07
    .sup
    0.07
    Act Density 0.004%

    No Known Activations