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

    Neuronpedia

    INDEX
    Explanations

    div

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    虎
    -0.06
     '_',
    -0.06
    =W
    -0.06
    Fed
    -0.06
    ”:
    -0.06
     Wan
    -0.06
    postgres
    -0.06
    mensagem
    -0.06
     bullied
    -0.06
    '↵↵
    -0.06
    POSITIVE LOGITS
    .CompilerServices
    0.06
    keyup
    0.06
    لی
    0.06
     συμβ
    0.06
    lepší
    0.06
    vou
    0.06
     цю
    0.06
     Jacqu
    0.06
    ioms
    0.06
     pij
    0.06
    Act Density 0.001%

    No Known Activations