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

    Neuronpedia

    INDEX
    Explanations

    level

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    63
    -0.06
     pře
    -0.06
     intellectual
    -0.06
     Nhĩ
    -0.06
     �
    -0.06
    -agent
    -0.06
    าส
    -0.05
     tactical
    -0.05
    -threat
    -0.05
     chased
    -0.05
    POSITIVE LOGITS
    grounds
    0.07
     paramInt
    0.07
    PDOException
    0.07
    results
    0.07
     genus
    0.07
    .street
    0.07
     nationalist
    0.07
     Ticket
    0.07
    truncate
    0.07
     assumption
    0.06
    Act Density 0.057%

    No Known Activations