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

    Neuronpedia

    INDEX
    Explanations

    click

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     governors
    -0.08
    Clientes
    -0.07
     konuş
    -0.07
     deaths
    -0.06
     carta
    -0.06
    zhou
    -0.06
    acas
    -0.06
    _Time
    -0.06
    CreatedAt
    -0.06
     choses
    -0.06
    POSITIVE LOGITS
    /**
↵
    0.07
    ,J
    0.07
        ↵
    0.06
    trl
    0.06
    ाइ
    0.06
     yılında
    0.06
    (effect
    0.06
     DACA
    0.06
    _optional
    0.06
    rij
    0.06
    Act Density 0.003%

    No Known Activations