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

    Neuronpedia

    INDEX
    Explanations

    multiplayer

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Goal
    -0.08
    .persistent
    -0.08
    Titulo
    -0.07
    /Base
    -0.07
    m
    -0.07
     الغ
    -0.07
    .lastname
    -0.07
    (Link
    -0.06
    Customers
    -0.06
    Respons
    -0.06
    POSITIVE LOGITS
     ja
    0.06
     trời
    0.06
    019
    0.06
    ={↵
    0.06
     {@
    0.06
     ***
    0.06
     mutlaka
    0.06
     <?=$
    0.06
     enraged
    0.06
     mysl
    0.06
    Act Density 0.020%

    No Known Activations