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

    Neuronpedia

    INDEX
    Explanations

    brexit

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     My
    -0.07
     Gratis
    -0.07
    egade
    -0.07
     вона
    -0.07
     to
    -0.06
     MY
    -0.06
     перевір
    -0.06
     Wed
    -0.06
     my
    -0.06
     مى
    -0.06
    POSITIVE LOGITS
    .md
    0.07
    .Filters
    0.06
    [];↵
    0.06
    ());↵↵↵
    0.06
    ρθ
    0.06
     verbally
    0.06
    abilité
    0.06
    Joint
    0.06
    viz
    0.06
     magically
    0.06
    Act Density 0.000%

    No Known Activations