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
     Δια
    -0.07
     기술
    -0.06
     wichtig
    -0.06
    ("**
    -0.06
     subtotal
    -0.06
    .joda
    -0.06
    Ｏ
    -0.06
     preschool
    -0.06
    PRO
    -0.06
    佛
    -0.06
    POSITIVE LOGITS
    asons
    0.07
     yapmak
    0.07
     ngang
    0.06
     gg
    0.06
     pě
    0.06
     almak
    0.06
    istant
    0.06
    abama
    0.06
    Subscribe
    0.06
    sport
    0.06
    Act Density 0.003%

    No Known Activations