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

    Neuronpedia

    INDEX
    Explanations

    speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drinkers
    -0.06
    Traversal
    -0.06
     Ende
    -0.06
     учрежд
    -0.06
     baseUrl
    -0.06
     Scandinavian
    -0.06
    .card
    -0.05
     onSubmit
    -0.05
    Occ
    -0.05
     certif
    -0.05
    POSITIVE LOGITS
     وش
    0.08
     khuôn
    0.07
    ">{{
    0.07
    alias
    0.07
     diễn
    0.07
    ront
    0.07
     hostages
    0.07
     embroidery
    0.06
    ;}
↵
    0.06
     más
    0.06
    Act Density 0.014%

    No Known Activations