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

    Neuronpedia

    INDEX
    Explanations

    music

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     scen
    -0.07
    addresses
    -0.06
    ._
    -0.06
     skepticism
    -0.06
     comprehension
    -0.06
     mostly
    -0.06
     melhor
    -0.06
    머니
    -0.06
     negotiation
    -0.06
     uk
    -0.06
    POSITIVE LOGITS
     Teams
    0.07
    -Compatible
    0.06
    اصيل
    0.06
    Impl
    0.06
    .Padding
    0.06
    +w
    0.06
    .el
    0.06
     CONCAT
    0.06
    .Toggle
    0.06
     خدمات
    0.06
    Act Density 0.028%

    No Known Activations