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

    Neuronpedia

    INDEX
    Explanations

    blog posts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Barker
    -0.07
    Jesus
    -0.07
    ncias
    -0.06
     немає
    -0.06
    ósito
    -0.06
     THR
    -0.06
     bothering
    -0.06
     JC
    -0.06
    .Packet
    -0.06
     tarım
    -0.06
    POSITIVE LOGITS
    )").
    0.07
    _workflow
    0.06
    traits
    0.06
    agnitude
    0.06
     applause
    0.06
    CloseOperation
    0.06
     misconduct
    0.06
    /kubernetes
    0.06
    结合
    0.06
    MethodImpl
    0.06
    Act Density 0.003%

    No Known Activations