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

    Neuronpedia

    INDEX
    Explanations

    -

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abel
    -0.06
     captivating
    -0.06
    (cnt
    -0.06
     strtotime
    -0.06
    PASSWORD
    -0.06
     ấm
    -0.06
     bağır
    -0.06
    >",↵
    -0.06
     tải
    -0.06
    /container
    -0.06
    POSITIVE LOGITS
    BAB
    0.07
    ildren
    0.07
     Пло
    0.06
    bab
    0.06
    WithOptions
    0.06
     JDBC
    0.06
     �
    0.06
    켓
    0.06
    Validator
    0.06
    hydro
    0.06
    Act Density 0.004%

    No Known Activations