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
    exus
    -0.07
    =plt
    -0.06
    ONUS
    -0.06
    <Path
    -0.06
    rada
    -0.06
     GW
    -0.06
    ZO
    -0.06
     quo
    -0.06
     På
    -0.06
     �
    -0.06
    POSITIVE LOGITS
    _header
    0.06
     mensagem
    0.06
     Evet
    0.06
     Copyright
    0.06
    :url
    0.06
     AtomicInteger
    0.06
    -await
    0.06
    tmp
    0.06
     alone
    0.06
     airs
    0.06
    Act Density 0.001%

    No Known Activations