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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    恶
    -0.06
    ریان
    -0.06
     полос
    -0.06
    ital
    -0.06
    [q
    -0.06
     dns
    -0.06
    .Abstractions
    -0.06
    <[
    -0.06
    锁
    -0.05
     zih
    -0.05
    POSITIVE LOGITS
     Meditation
    0.07
    OPSIS
    0.07
     monoc
    0.06
     READ
    0.06
     evaluate
    0.06
    _clusters
    0.06
    �
    0.06
     Dram
    0.06
     recruited
    0.06
     Foundations
    0.06
    Act Density 0.000%

    No Known Activations